{ "schema": "honesty.leaderboard.manifest.v1", "purpose": "Compact discovery of existing public profiles and source-specific evidence; not a new ranking or assessment.", "source": { "url": "/leaderboard/observatory.json", "bytes": 46635083, "sha256": "e262b95f0f056d3c53d8dbfc5371d47874f06144e1f554b831ef2c160b5d0c2f", "schema": "honesty-mark-observatory/v0.1", "edition": "2026-10-13", "status": "local_research_preview", "publication_performed": false }, "date_note": "The source edition and status fields are retained verbatim; they are not a current verification date or the publication date of this generated manifest.", "overall_ranking_status": "Common basket and award standard under development", "profile_count": 489, "observation_count": 2887, "corrections": "/leaderboard/corrections.json", "human_index": "/leaderboard/records/", "sources": [ { "comparison_caution": "Each declared development bank has separate cohorts and denominators. Low effort, unequal output caps, dependent phases and client-load confounds limit interpretation. Question selection and explicit update metrics use declared opportunity counts. Formal conflict certificates measure evidence support, not bibliographic citation integrity. The scoped research index uses published policy weights; it awards no certification.", "id": "honesty", "import_status": "imported", "metrics": [ "justified answers", "appropriate abstention", "unsupported commitments", "unnecessary abstention", "conflict certificates", "resolving questions", "revision outcomes", "delivery failures" ], "name": "Honesty.tools evidence benchmark", "organization": "Honesty.tools", "pillars": [ "evidence_support", "uncertainty", "belief_revision" ], "reviewed_on": "2026-10-11", "url": "https://www.honesty.tools/benchmark/" }, { "comparison_caution": "Document summarization judged by HHEM-2.3 on a private dataset. Hallucination and consistency are complements. Native table lacks trial-level uncertainty; answer rate is essential context.", "id": "vectara", "import_status": "imported", "metrics": [ "hallucination rate", "factual consistency", "answer rate", "summary length" ], "name": "Vectara Hallucination Leaderboard", "organization": "Vectara", "pillars": [ "evidence_support" ], "reviewed_on": "2026-10-11", "url": "https://github.com/vectara/hallucination-leaderboard" }, { "comparison_caution": "Historical paper full-set results, not the current private-split leaderboard. Source explicit-honest and lie categories use elicited response consistency as a belief proxy; no direct proof of intentions. Evasion/no belief is separate from explicit honesty. The 1-minus-lie honesty score is not imported. @10 is a dependent repeated-pressure condition, not ten independent votes. Missing @10 values stay missing. No overall ranking or Mark admission.", "id": "mask", "import_status": "imported", "metrics": [ "Elicited belief accuracy", "Explicit honest @10", "Explicit honest responses", "Lie classification @10", "Lie classification rate" ], "name": "MASK · paper v1 (2025)", "organization": "Center for AI Safety / Scale AI", "pillars": [ "factual_accuracy", "pressure_resistance" ], "reviewed_on": "2026-10-13", "url": "https://arxiv.org/html/2503.03750v1" }, { "comparison_caution": "Historical paper chart labels, not the current website leaderboard. Whole-number rounding retained. Index rewards correct answers and penalizes incorrect answers; always abstaining scores zero. Hallucination rate is incorrect/(partial+incorrect+not attempted), not incorrect/all or incorrect/attempted. Single-pass author-judged results, no calibration confidence claims, no Mark admission.", "id": "aa_omniscience", "import_status": "imported", "metrics": [ "Hallucination rate (paper chart)", "Omniscience Index (paper chart)" ], "name": "AA-Omniscience · paper v1 (2025)", "organization": "Artificial Analysis", "pillars": [ "factual_accuracy", "uncertainty" ], "reviewed_on": "2026-10-13", "url": "https://arxiv.org/html/2511.13029v1" }, { "comparison_caution": "21 first-party OpenAI rows in pinned MIT result table, historical through July 2025. Missing abstention breakdown and trial counts stay unknown; third-party reported rows excluded.", "id": "simpleqa", "import_status": "imported", "metrics": [ "Correct answers" ], "name": "SimpleQA · historical provider reports", "organization": "OpenAI", "pillars": [ "factual_accuracy" ], "reviewed_on": "2026-10-11", "url": "https://openai.com/index/introducing-simpleqa/" }, { "comparison_caution": "Historical 2021 v0 generation baselines on misconception-focused questions. Truthfulness credits non-answers; informativeness must be read alongside it. Marginal truth/info rates do not establish the joint truthful-and-informative rate. Default QA prompting and UnifiedQA without a prefix are separate cohorts. GPT-judge is an overlapping automatic assessment, not an independent replication or a calibrated confidence estimate. The 2025 binary task and updated-reference baseline table are excluded. These are authors-reported aggregates, not current-model rankings.", "id": "truthfulqa", "import_status": "imported", "metrics": [ "Human-rated truthfulness", "Human-rated informativeness", "GPT-judge truthfulness (context)" ], "name": "TruthfulQA · historical v0 (2021)", "organization": "TruthfulQA authors", "pillars": [ "factual_accuracy" ], "reviewed_on": "2026-10-11", "url": "https://arxiv.org/abs/2109.07958" }, { "comparison_caution": "Original December 2024 FACTS Grounding, Table 6; not Grounding v2 or the successor FACTS suite. Three judge models evaluate the same responses; split/judge cells and their published average are dependent views, not extra model trials. The source eligibility filter treats disqualified replies as inaccurate. Source-label versions and execution settings are not fully pinned. Publisher-reported context only; no cross-source identity join, ranking or Honesty Mark admission.", "id": "facts", "import_status": "imported", "metrics": [ "Original final factuality after disqualification" ], "name": "FACTS Grounding · original 2024 table", "organization": "Google DeepMind / Google Research", "pillars": [ "evidence_support" ], "reviewed_on": "2026-10-13", "url": "https://deepmind.google/blog/facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models/" }, { "comparison_caution": "Historical paper Table4 averages, not the noncommercial repository result CSV. Accuracy on answerable questions and abstention recall on should-abstain questions have different populations. Source excludes invalid correctness-judge outputs; no pooled counts or joint utility reconstructed. Average weighting and per-model realized counts are not recoverable from this table. No overall ranking or Mark admission.", "id": "abstentionbench", "import_status": "imported", "metrics": [ "Average abstention recall", "Average answerable-question accuracy" ], "name": "AbstentionBench · paper Table 4 (2025)", "organization": "AbstentionBench authors / Meta research", "pillars": [ "factual_accuracy", "uncertainty" ], "reviewed_on": "2026-10-13", "url": "https://arxiv.org/html/2506.09038v1" }, { "comparison_caution": "Historical 2024 authors-reported chart aggregates with deterministic decoding and task-specific prompts. Exact endpoint revisions, per-response counts and uncertainty are not established by the charts. Unanswerable/inconsistent scores are attributed to the paper v1 strict keyword matching scheme and do not validate arbitrary abstention explanations. Counterfactual adherence rewards following the supplied fictional premise; it is not an alignment or world-truth score. Baselines have different context/prompt conditions and are companion outcomes, not causal tool effects.", "id": "faitheval", "import_status": "imported", "metrics": [ "Unknown-answer match", "Conflict-answer match", "Counterfactual context adherence", "Companion baseline accuracy" ], "name": "FaithEval · historical 2024", "organization": "Salesforce AI Research", "pillars": [ "evidence_support", "uncertainty" ], "reviewed_on": "2026-10-11", "url": "https://github.com/SalesforceAIResearch/FaithEval" }, { "comparison_caution": "Selected ASQA VANILLA rows from Table 18; TRUE-NLI citation scores and answer EM recall, mean and SD across three runs. Retrieval and instructions define separate cohorts. Oasst-33B citation precision differs between Tables 7 and 18; the Table 18 value is retained with the discrepancy disclosed.", "id": "alce", "import_status": "imported", "metrics": [ "Answer EM recall", "Citation recall", "Citation precision" ], "name": "ALCE · historical 2023", "organization": "ALCE authors", "pillars": [ "citation_integrity" ], "reviewed_on": "2026-10-11", "url": "https://arxiv.org/abs/2305.14627" }, { "comparison_caution": "Official PDF/forum require browser verification; direct PDF/API returns 403. Official conference event links only to the same OpenReview forum. No accessible author repository or authorized numerical table found.", "id": "agm", "import_status": "blocked_access", "metrics": [ "formal belief revision rationality" ], "name": "AGM-Bench", "organization": "AGM-Bench authors", "pillars": [ "belief_revision" ], "reviewed_on": "2026-10-13", "url": "https://openreview.net/pdf?id=2s1BujG84C" }, { "comparison_caution": "Historical author-reported Table A1; three prompting methods are separate cohorts. BU/BM measure appropriate update and retention, while BREU equally averages them and is not independent evidence. This suppression-task convention uses contextual/commonsense judgments, not universal deductive entailment. Exact provider, revision, sampling and realized per-run denominators are not bound by the table. No cross-source model join or full Mark admission.", "id": "belief_r", "import_status": "imported", "metrics": [ "Belief Update accuracy (context)", "Belief Maintain accuracy (context)", "BREU balanced update/retain accuracy (context)" ], "name": "Belief-R", "organization": "Belief-R authors", "pillars": [ "belief_revision" ], "reviewed_on": "2026-10-13", "url": "https://arxiv.org/html/2406.19764v2#A3.T1" }, { "comparison_caution": "Author-reported three-run means on 200 private multiple-choice questions. Reported SD is run-to-run variation, not SE or a confidence interval. Sections 3.2/5.3 state refusals and unparseable outputs receive random-choice probability .25, while Table 2 calls n pooled non-refused responses. Actual scoring population is unresolved; n is contextual only. No source code, execution, private questions or per-run denominators reconstructed. No aliases or full Mark admission; paper model labels retain effort variants.", "id": "confidencebench", "import_status": "imported", "metrics": [ "Brier score (context)", "Answer accuracy (context)", "Expected Calibration Error (context)" ], "name": "ConfidenceBench", "organization": "ConfidenceBench authors", "pillars": [ "uncertainty", "factual_accuracy" ], "reviewed_on": "2026-10-13", "url": "https://arxiv.org/html/2607.20526v1#A1.T2" }, { "comparison_caution": "Publisher-reported Figure 1 context; no ranking, cross-source model join or Honesty Mark admission. Bloom generates adaptive scenarios rather than one identical fixed question bank for every model. Model labels, seed settings and nominal sample sizes do not attest execution routes or realized trial counts. Printed two-decimal means are retained; SD bars are not numerically reconstructed. The article says 16 models but the figure and publication-time sweep list 17; all 17 plotted labels are retained. Only sycophancy is mapped to an honesty dimension; the other three are distinct behavioral context.", "id": "bloom", "import_status": "imported", "metrics": [ "Delusional sycophancy elicitation rate", "Instructed long-horizon sabotage elicitation rate", "Self-preservation elicitation rate", "Self-preferential bias elicitation rate" ], "name": "Bloom behavioral evaluations · published 2025 cohort", "organization": "Anthropic", "pillars": [ "pressure_resistance", "behavioral_context" ], "reviewed_on": "2026-10-13", "url": "https://alignment.anthropic.com/2025/bloom-auto-evals/" }, { "comparison_caution": "Agent/scaffold results on GAIA and clean airline τ-bench. HAL reliability excludes safety; metric aggregates overlap their components. Source standard errors are not confidence intervals. Model release dates are not evaluation dates.", "id": "hal", "import_status": "imported", "metrics": [ "Task success", "HAL reliability", "Consistency", "Outcome consistency", "Action-distribution consistency", "Action-sequence consistency", "Resource consistency", "Confidence consistency", "Predictability", "Calibration: 1 − ECE", "Confidence discrimination", "Brier quality: 1 − Brier", "Risk–coverage quality", "Robustness", "Tool-failure robustness", "Format robustness", "Prompt robustness", "Constraint-risk score", "Constraint compliance", "Conditional severity: inverted" ], "name": "HAL Agent Reliability", "organization": "SAgE / Princeton University", "pillars": [ "calibration", "constraint_compliance", "robustness", "reliability" ], "reviewed_on": "2026-10-11", "url": "https://hal.cs.princeton.edu/reliability/" }, { "comparison_caution": "Nine source model labels, two cue scenarios. All 18 rates reproduced from retained judge explanations using the original keyword heuristic. Unequal retained samples, no accuracy companion; a lower change rate is not a validated honesty score. Historical setup, not a current frontier-model comparison.", "id": "behonest", "import_status": "imported", "metrics": [ "Heuristic answer-change rate: persona", "Heuristic answer-change rate: preference" ], "name": "BeHonest · historical 2024", "organization": "BeHonest authors / GAIR", "pillars": [ "pressure_resistance" ], "reviewed_on": "2026-10-11", "url": "https://github.com/GAIR-NLP/BeHonest" }, { "comparison_caution": "Independent publisher-reported SimpleQA Verified accuracy; aggregate context only. Distinct from original SimpleQA and Google F1. Epoch documents an anti-abstention prompt change on 2026-08-27, but the retained CSV includes earlier runs and does not bind each row to prompt, judge, provider, or execution configuration. Effort suffixes remain source labels. Scored denominators and incorrect/not-attempted counts are unknown. No cross-source identity join, honesty rank, or Mark admission.", "id": "epoch_simpleqa_verified", "import_status": "imported", "metrics": [ "Source-reported correct-answer rate (context)" ], "name": "Epoch AI · SimpleQA Verified", "organization": "Epoch AI", "pillars": [ "factual_accuracy" ], "reviewed_on": "2026-10-13", "url": "https://epoch.ai/benchmarks/simple-qa-verified" } ], "profiles": [ { "id": "hm-0031d6ad0c256558f17d", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0031d6ad0c256558f17d.json", "report": "/leaderboard/reports/hm-0031d6ad0c256558f17d.md", "plan": "/leaderboard/plans/hm-0031d6ad0c256558f17d.md" }, { "id": "hm-00c62eb3ed5e65e6da77", "model_label": "gpt-3.5-turbo", "lab": "OpenAI", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-00c62eb3ed5e65e6da77.json", "report": "/leaderboard/reports/hm-00c62eb3ed5e65e6da77.md", "plan": "/leaderboard/plans/hm-00c62eb3ed5e65e6da77.md" }, { "id": "hm-017c60a9ac65158bab35", "model_label": "ibm-granite/granite-4.0-h-small", "lab": "IBM", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-017c60a9ac65158bab35.json", "report": "/leaderboard/reports/hm-017c60a9ac65158bab35.md", "plan": "/leaderboard/plans/hm-017c60a9ac65158bab35.md" }, { "id": "hm-018c77c437ef0e058ee7", "model_label": "openai/gpt-5.5", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-018c77c437ef0e058ee7.json", "report": "/leaderboard/reports/hm-018c77c437ef0e058ee7.md", "plan": "/leaderboard/plans/hm-018c77c437ef0e058ee7.md" }, { "id": "hm-038d7672fcdfb6eea466", "model_label": "claude-opus-4-8_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-038d7672fcdfb6eea466.json", "report": "/leaderboard/reports/hm-038d7672fcdfb6eea466.md", "plan": "/leaderboard/plans/hm-038d7672fcdfb6eea466.md" }, { "id": "hm-0399b8dfc3714dd0a778", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0399b8dfc3714dd0a778.json", "report": "/leaderboard/reports/hm-0399b8dfc3714dd0a778.md", "plan": "/leaderboard/plans/hm-0399b8dfc3714dd0a778.md" }, { "id": "hm-04c9858909c1684ce76f", "model_label": "o4-mini-low", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-04c9858909c1684ce76f.json", "report": "/leaderboard/reports/hm-04c9858909c1684ce76f.md", "plan": "/leaderboard/plans/hm-04c9858909c1684ce76f.md" }, { "id": "hm-0543729bf84b36980fda", "model_label": "Gemini 2.5 Flash", "lab": "Google", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0543729bf84b36980fda.json", "report": "/leaderboard/reports/hm-0543729bf84b36980fda.md", "plan": "/leaderboard/plans/hm-0543729bf84b36980fda.md" }, { "id": "hm-057b6558c4e2c8c3343d", "model_label": "claude-sonnet-4-5-20250929", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-057b6558c4e2c8c3343d.json", "report": "/leaderboard/reports/hm-057b6558c4e2c8c3343d.md", "plan": "/leaderboard/plans/hm-057b6558c4e2c8c3343d.md" }, { "id": "hm-05cea6c91a2f0a7b00c1", "model_label": "Command R+", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-05cea6c91a2f0a7b00c1.json", "report": "/leaderboard/reports/hm-05cea6c91a2f0a7b00c1.md", "plan": "/leaderboard/plans/hm-05cea6c91a2f0a7b00c1.md" }, { "id": "hm-05d6dac5a5e782f7d928", "model_label": "OpenAI o1-mini", "lab": "OpenAI", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-05d6dac5a5e782f7d928.json", "report": "/leaderboard/reports/hm-05d6dac5a5e782f7d928.md", "plan": "/leaderboard/plans/hm-05d6dac5a5e782f7d928.md" }, { "id": "hm-066320c739f48308d70b", "model_label": "anthropic/claude-opus-4-1-20250805", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-066320c739f48308d70b.json", "report": "/leaderboard/reports/hm-066320c739f48308d70b.md", "plan": "/leaderboard/plans/hm-066320c739f48308d70b.md" }, { "id": "hm-06a65c72fd915affad90", "model_label": "Mixtral (8x22B)", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-06a65c72fd915affad90.json", "report": "/leaderboard/reports/hm-06a65c72fd915affad90.md", "plan": "/leaderboard/plans/hm-06a65c72fd915affad90.md" }, { "id": "hm-06c2619f1fc3842ec28c", "model_label": "o3-mini-2025-01-31∗", "lab": "OpenAI", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-06c2619f1fc3842ec28c.json", "report": "/leaderboard/reports/hm-06c2619f1fc3842ec28c.md", "plan": "/leaderboard/plans/hm-06c2619f1fc3842ec28c.md" }, { "id": "hm-06f713ccf7c2dbd7399f", "model_label": "gpt-6-sol_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-06f713ccf7c2dbd7399f.json", "report": "/leaderboard/reports/hm-06f713ccf7c2dbd7399f.md", "plan": "/leaderboard/plans/hm-06f713ccf7c2dbd7399f.md" }, { "id": "hm-07d4d9d86439e7a521c9", "model_label": "zai-org/GLM-4.5-AIR-FP8", "lab": "Z.ai", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-07d4d9d86439e7a521c9.json", "report": "/leaderboard/reports/hm-07d4d9d86439e7a521c9.md", "plan": "/leaderboard/plans/hm-07d4d9d86439e7a521c9.md" }, { "id": "hm-07f2e0ec005395c96396", "model_label": "grok-4.7_xhigh", "lab": "xAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-07f2e0ec005395c96396.json", "report": "/leaderboard/reports/hm-07f2e0ec005395c96396.md", "plan": "/leaderboard/plans/hm-07f2e0ec005395c96396.md" }, { "id": "hm-084da4012520359ef1ba", "model_label": "gemma-4-31b-it", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-084da4012520359ef1ba.json", "report": "/leaderboard/reports/hm-084da4012520359ef1ba.md", "plan": "/leaderboard/plans/hm-084da4012520359ef1ba.md" }, { "id": "hm-08ca0b4aa1ff6a42ad67", "model_label": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "lab": "Meta", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-08ca0b4aa1ff6a42ad67.json", "report": "/leaderboard/reports/hm-08ca0b4aa1ff6a42ad67.md", "plan": "/leaderboard/plans/hm-08ca0b4aa1ff6a42ad67.md" }, { "id": "hm-08e3214cda106f1c3b55", "model_label": "gpt-5-nano-2025-08-07_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-08e3214cda106f1c3b55.json", "report": "/leaderboard/reports/hm-08e3214cda106f1c3b55.md", "plan": "/leaderboard/plans/hm-08e3214cda106f1c3b55.md" }, { "id": "hm-0a4c9aa18ab1e957de7f", "model_label": "Phi-3.5-mini-instruct", "lab": "Microsoft", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0a4c9aa18ab1e957de7f.json", "report": "/leaderboard/reports/hm-0a4c9aa18ab1e957de7f.md", "plan": "/leaderboard/plans/hm-0a4c9aa18ab1e957de7f.md" }, { "id": "hm-0ac80af653e096d8adef", "model_label": "qwen3-max-2025-09-23", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0ac80af653e096d8adef.json", "report": "/leaderboard/reports/hm-0ac80af653e096d8adef.md", "plan": "/leaderboard/plans/hm-0ac80af653e096d8adef.md" }, { "id": "hm-0c5ed0f58ec6e05c0506", "model_label": "o3-mini-high", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0c5ed0f58ec6e05c0506.json", "report": "/leaderboard/reports/hm-0c5ed0f58ec6e05c0506.md", "plan": "/leaderboard/plans/hm-0c5ed0f58ec6e05c0506.md" }, { "id": "hm-0d25fcf0df93b95d9f00", "model_label": "Phi-3-medium-128k-instruct", "lab": "Microsoft", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0d25fcf0df93b95d9f00.json", "report": "/leaderboard/reports/hm-0d25fcf0df93b95d9f00.md", "plan": "/leaderboard/plans/hm-0d25fcf0df93b95d9f00.md" }, { "id": "hm-0df1d5d9d702394a89ab", "model_label": "NVIDIA Nemotron Nano 9B V2", "lab": "NVIDIA", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-0df1d5d9d702394a89ab.json", "report": "/leaderboard/reports/hm-0df1d5d9d702394a89ab.md", "plan": "/leaderboard/plans/hm-0df1d5d9d702394a89ab.md" }, { "id": "hm-10938d9d16afd6c87c97", "model_label": "mistralai/ministral-3-8b-2512", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-10938d9d16afd6c87c97.json", "report": "/leaderboard/reports/hm-10938d9d16afd6c87c97.md", "plan": "/leaderboard/plans/hm-10938d9d16afd6c87c97.md" }, { "id": "hm-10e35ef11cc592ac7f48", "model_label": "qwen3.6-plus", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-10e35ef11cc592ac7f48.json", "report": "/leaderboard/reports/hm-10e35ef11cc592ac7f48.md", "plan": "/leaderboard/plans/hm-10e35ef11cc592ac7f48.md" }, { "id": "hm-11793e0afb6da10ad1b0", "model_label": "GPT-4o", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-11793e0afb6da10ad1b0.json", "report": "/leaderboard/reports/hm-11793e0afb6da10ad1b0.md", "plan": "/leaderboard/plans/hm-11793e0afb6da10ad1b0.md" }, { "id": "hm-1187b52b40a6fd0a957e", "model_label": "qwen/qwen3-14b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1187b52b40a6fd0a957e.json", "report": "/leaderboard/reports/hm-1187b52b40a6fd0a957e.md", "plan": "/leaderboard/plans/hm-1187b52b40a6fd0a957e.md" }, { "id": "hm-11c57014121e8b20b2aa", "model_label": "xai-org/grok-4-fast-non-reasoning", "lab": "xAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-11c57014121e8b20b2aa.json", "report": "/leaderboard/reports/hm-11c57014121e8b20b2aa.md", "plan": "/leaderboard/plans/hm-11c57014121e8b20b2aa.md" }, { "id": "hm-11cb3eb4894be7796865", "model_label": "EXAONE 4.0 32B", "lab": "LG AI Research", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-11cb3eb4894be7796865.json", "report": "/leaderboard/reports/hm-11cb3eb4894be7796865.md", "plan": "/leaderboard/plans/hm-11cb3eb4894be7796865.md" }, { "id": "hm-11dfb4fdf490b40e3d0c", "model_label": "zai-org/GLM-4.6", "lab": "Z.ai", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-11dfb4fdf490b40e3d0c.json", "report": "/leaderboard/reports/hm-11dfb4fdf490b40e3d0c.md", "plan": "/leaderboard/plans/hm-11dfb4fdf490b40e3d0c.md" }, { "id": "hm-120117f67f8319156e2d", "model_label": "gpt-5.5_xhigh", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-120117f67f8319156e2d.json", "report": "/leaderboard/reports/hm-120117f67f8319156e2d.md", "plan": "/leaderboard/plans/hm-120117f67f8319156e2d.md" }, { "id": "hm-1210c2bc40bd3e68f112", "model_label": "Mistral 7B v0.3", "lab": "Mistral AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1210c2bc40bd3e68f112.json", "report": "/leaderboard/reports/hm-1210c2bc40bd3e68f112.md", "plan": "/leaderboard/plans/hm-1210c2bc40bd3e68f112.md" }, { "id": "hm-122e58836f7522ab248c", "model_label": "gpt-4o-2024-08-06", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-122e58836f7522ab248c.json", "report": "/leaderboard/reports/hm-122e58836f7522ab248c.md", "plan": "/leaderboard/plans/hm-122e58836f7522ab248c.md" }, { "id": "hm-1263bca054479842ea63", "model_label": "llama-33-70b-instruct", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1263bca054479842ea63.json", "report": "/leaderboard/reports/hm-1263bca054479842ea63.md", "plan": "/leaderboard/plans/hm-1263bca054479842ea63.md" }, { "id": "hm-12c9b44e86cae91732b8", "model_label": "o3-2025-04-16_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-12c9b44e86cae91732b8.json", "report": "/leaderboard/reports/hm-12c9b44e86cae91732b8.md", "plan": "/leaderboard/plans/hm-12c9b44e86cae91732b8.md" }, { "id": "hm-12e82cebd27f67cb086b", "model_label": "Llama Nemotron Super 49B V1.5", "lab": "NVIDIA", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-12e82cebd27f67cb086b.json", "report": "/leaderboard/reports/hm-12e82cebd27f67cb086b.md", "plan": "/leaderboard/plans/hm-12e82cebd27f67cb086b.md" }, { "id": "hm-13ed762290a2c6cab976", "model_label": "Claude-3 Haiku", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-13ed762290a2c6cab976.json", "report": "/leaderboard/reports/hm-13ed762290a2c6cab976.md", "plan": "/leaderboard/plans/hm-13ed762290a2c6cab976.md" }, { "id": "hm-14147a30fc5fa942dd79", "model_label": "grok-4.3_high", "lab": "xAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-14147a30fc5fa942dd79.json", "report": "/leaderboard/reports/hm-14147a30fc5fa942dd79.md", "plan": "/leaderboard/plans/hm-14147a30fc5fa942dd79.md" }, { "id": "hm-1490a70372e9f8aa1cfc", "model_label": "GPT-5.1", "lab": "OpenAI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1490a70372e9f8aa1cfc.json", "report": "/leaderboard/reports/hm-1490a70372e9f8aa1cfc.md", "plan": "/leaderboard/plans/hm-1490a70372e9f8aa1cfc.md" }, { "id": "hm-1592f195c0008bcc4776", "model_label": "gpt-5.4-2026-03-05_xhigh", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1592f195c0008bcc4776.json", "report": "/leaderboard/reports/hm-1592f195c0008bcc4776.md", "plan": "/leaderboard/plans/hm-1592f195c0008bcc4776.md" }, { "id": "hm-159e82e64a4ceeafb243", "model_label": "qwen3.5-plus", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-159e82e64a4ceeafb243.json", "report": "/leaderboard/reports/hm-159e82e64a4ceeafb243.md", "plan": "/leaderboard/plans/hm-159e82e64a4ceeafb243.md" }, { "id": "hm-1657c6c37ffb97cc12ff", "model_label": "gemini-3.1-pro-preview_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1657c6c37ffb97cc12ff.json", "report": "/leaderboard/reports/hm-1657c6c37ffb97cc12ff.md", "plan": "/leaderboard/plans/hm-1657c6c37ffb97cc12ff.md" }, { "id": "hm-168de82a93a83fb42df4", "model_label": "zai-org/glm-4p7", "lab": "Z.ai", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-168de82a93a83fb42df4.json", "report": "/leaderboard/reports/hm-168de82a93a83fb42df4.md", "plan": "/leaderboard/plans/hm-168de82a93a83fb42df4.md" }, { "id": "hm-16a9be924b705dc5356d", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-16a9be924b705dc5356d.json", "report": "/leaderboard/reports/hm-16a9be924b705dc5356d.md", "plan": "/leaderboard/plans/hm-16a9be924b705dc5356d.md" }, { "id": "hm-177e78abedc6f2807a8a", "model_label": "google/gemini-3.1-pro-preview", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-177e78abedc6f2807a8a.json", "report": "/leaderboard/reports/hm-177e78abedc6f2807a8a.md", "plan": "/leaderboard/plans/hm-177e78abedc6f2807a8a.md" }, { "id": "hm-17b02d2dfd5d4fc21027", "model_label": "GPT-5 mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-17b02d2dfd5d4fc21027.json", "report": "/leaderboard/reports/hm-17b02d2dfd5d4fc21027.md", "plan": "/leaderboard/plans/hm-17b02d2dfd5d4fc21027.md" }, { "id": "hm-18cf4f1899df0ca58a2b", "model_label": "grok-4.6_xhigh", "lab": "xAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-18cf4f1899df0ca58a2b.json", "report": "/leaderboard/reports/hm-18cf4f1899df0ca58a2b.md", "plan": "/leaderboard/plans/hm-18cf4f1899df0ca58a2b.md" }, { "id": "hm-18d2e039b0220883d22e", "model_label": "Gemini 1.5 Pro", "lab": "Google", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-18d2e039b0220883d22e.json", "report": "/leaderboard/reports/hm-18d2e039b0220883d22e.md", "plan": "/leaderboard/plans/hm-18d2e039b0220883d22e.md" }, { "id": "hm-19d27502fbb89049a1a6", "model_label": "mistralai/ministral-3-3b-2512", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-19d27502fbb89049a1a6.json", "report": "/leaderboard/reports/hm-19d27502fbb89049a1a6.md", "plan": "/leaderboard/plans/hm-19d27502fbb89049a1a6.md" }, { "id": "hm-1a1b8e4b8c4eacd19ee6", "model_label": "claude-3-5-sonnet-20240620", "lab": "Anthropic", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1a1b8e4b8c4eacd19ee6.json", "report": "/leaderboard/reports/hm-1a1b8e4b8c4eacd19ee6.md", "plan": "/leaderboard/plans/hm-1a1b8e4b8c4eacd19ee6.md" }, { "id": "hm-1d077f5e43f513144c84", "model_label": "LLaMA-33B", "lab": "Meta", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1d077f5e43f513144c84.json", "report": "/leaderboard/reports/hm-1d077f5e43f513144c84.md", "plan": "/leaderboard/plans/hm-1d077f5e43f513144c84.md" }, { "id": "hm-1d48c93a8d6d8400daa6", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1d48c93a8d6d8400daa6.json", "report": "/leaderboard/reports/hm-1d48c93a8d6d8400daa6.md", "plan": "/leaderboard/plans/hm-1d48c93a8d6d8400daa6.md" }, { "id": "hm-1dc43218551c203c811c", "model_label": "GPT-5", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1dc43218551c203c811c.json", "report": "/leaderboard/reports/hm-1dc43218551c203c811c.md", "plan": "/leaderboard/plans/hm-1dc43218551c203c811c.md" }, { "id": "hm-1e583ae939fbdf8312a4", "model_label": "GPT-4 Turbo", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1e583ae939fbdf8312a4.json", "report": "/leaderboard/reports/hm-1e583ae939fbdf8312a4.md", "plan": "/leaderboard/plans/hm-1e583ae939fbdf8312a4.md" }, { "id": "hm-1ed2c370ef21e7274577", "model_label": "o1-2024-12-17_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1ed2c370ef21e7274577.json", "report": "/leaderboard/reports/hm-1ed2c370ef21e7274577.md", "plan": "/leaderboard/plans/hm-1ed2c370ef21e7274577.md" }, { "id": "hm-1ef46bc3f19eee784726", "model_label": "GPT-OSS-120B", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1ef46bc3f19eee784726.json", "report": "/leaderboard/reports/hm-1ef46bc3f19eee784726.md", "plan": "/leaderboard/plans/hm-1ef46bc3f19eee784726.md" }, { "id": "hm-1f4f7585c2a94c609129", "model_label": "qwen15-110b-chat", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1f4f7585c2a94c609129.json", "report": "/leaderboard/reports/hm-1f4f7585c2a94c609129.md", "plan": "/leaderboard/plans/hm-1f4f7585c2a94c609129.md" }, { "id": "hm-1fef6355c48f178dd77b", "model_label": "Claude-3 Haiku", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-1fef6355c48f178dd77b.json", "report": "/leaderboard/reports/hm-1fef6355c48f178dd77b.md", "plan": "/leaderboard/plans/hm-1fef6355c48f178dd77b.md" }, { "id": "hm-21055553e1af885da600", "model_label": "anthropic/claude-sonnet-5.5", "lab": "Anthropic", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-21055553e1af885da600.json", "report": "/leaderboard/reports/hm-21055553e1af885da600.md", "plan": "/leaderboard/plans/hm-21055553e1af885da600.md" }, { "id": "hm-211e3308d2cf5fca0024", "model_label": "Llama-3-70B-Instruct", "lab": "Meta", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-211e3308d2cf5fca0024.json", "report": "/leaderboard/reports/hm-211e3308d2cf5fca0024.md", "plan": "/leaderboard/plans/hm-211e3308d2cf5fca0024.md" }, { "id": "hm-2141e0f2322655869dff", "model_label": "Grok-4", "lab": "xAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2141e0f2322655869dff.json", "report": "/leaderboard/reports/hm-2141e0f2322655869dff.md", "plan": "/leaderboard/plans/hm-2141e0f2322655869dff.md" }, { "id": "hm-21a8c0ae87b45d949eda", "model_label": "qwen3.6-max-preview", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-21a8c0ae87b45d949eda.json", "report": "/leaderboard/reports/hm-21a8c0ae87b45d949eda.md", "plan": "/leaderboard/plans/hm-21a8c0ae87b45d949eda.md" }, { "id": "hm-21c9a4cbfdeaf0412193", "model_label": "Kimi k2", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-21c9a4cbfdeaf0412193.json", "report": "/leaderboard/reports/hm-21c9a4cbfdeaf0412193.md", "plan": "/leaderboard/plans/hm-21c9a4cbfdeaf0412193.md" }, { "id": "hm-22de079b73829026ac9e", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-22de079b73829026ac9e.json", "report": "/leaderboard/reports/hm-22de079b73829026ac9e.md", "plan": "/leaderboard/plans/hm-22de079b73829026ac9e.md" }, { "id": "hm-230dc1ead22ec5aac6e5", "model_label": "gpt-6.1-sol_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-230dc1ead22ec5aac6e5.json", "report": "/leaderboard/reports/hm-230dc1ead22ec5aac6e5.md", "plan": "/leaderboard/plans/hm-230dc1ead22ec5aac6e5.md" }, { "id": "hm-236bd02fd1b2bac8dbe1", "model_label": "GPT-4o", "lab": "OpenAI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-236bd02fd1b2bac8dbe1.json", "report": "/leaderboard/reports/hm-236bd02fd1b2bac8dbe1.md", "plan": "/leaderboard/plans/hm-236bd02fd1b2bac8dbe1.md" }, { "id": "hm-24ca93e7278d6029bb7d", "model_label": "llama3-8b-instruct", "lab": "Meta", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-24ca93e7278d6029bb7d.json", "report": "/leaderboard/reports/hm-24ca93e7278d6029bb7d.md", "plan": "/leaderboard/plans/hm-24ca93e7278d6029bb7d.md" }, { "id": "hm-24ef2c93d1a8ff3a7523", "model_label": "openai/gpt-oss-120b", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-24ef2c93d1a8ff3a7523.json", "report": "/leaderboard/reports/hm-24ef2c93d1a8ff3a7523.md", "plan": "/leaderboard/plans/hm-24ef2c93d1a8ff3a7523.md" }, { "id": "hm-24efb31559af707d10f2", "model_label": "OLMo 7B", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-24efb31559af707d10f2.json", "report": "/leaderboard/reports/hm-24efb31559af707d10f2.md", "plan": "/leaderboard/plans/hm-24efb31559af707d10f2.md" }, { "id": "hm-2636544fcad5fd6eec13", "model_label": "glm-5.1", "lab": "Z.ai (Zhipu AI)", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2636544fcad5fd6eec13.json", "report": "/leaderboard/reports/hm-2636544fcad5fd6eec13.md", "plan": "/leaderboard/plans/hm-2636544fcad5fd6eec13.md" }, { "id": "hm-26977b35aaabf8a9b19f", "model_label": "Qwen2.5 32B", "lab": "Alibaba", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-26977b35aaabf8a9b19f.json", "report": "/leaderboard/reports/hm-26977b35aaabf8a9b19f.md", "plan": "/leaderboard/plans/hm-26977b35aaabf8a9b19f.md" }, { "id": "hm-26b9c6ba08108065ea06", "model_label": "amazon/nova-2-lite-v1:0", "lab": "Amazon", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-26b9c6ba08108065ea06.json", "report": "/leaderboard/reports/hm-26b9c6ba08108065ea06.md", "plan": "/leaderboard/plans/hm-26b9c6ba08108065ea06.md" }, { "id": "hm-26c9da8b6b61641fb165", "model_label": "Claude Opus 4.6", "lab": "Anthropic", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-26c9da8b6b61641fb165.json", "report": "/leaderboard/reports/hm-26c9da8b6b61641fb165.md", "plan": "/leaderboard/plans/hm-26c9da8b6b61641fb165.md" }, { "id": "hm-279523f4768869074f6c", "model_label": "gpt-4.1-mini-2025-04-14", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-279523f4768869074f6c.json", "report": "/leaderboard/reports/hm-279523f4768869074f6c.md", "plan": "/leaderboard/plans/hm-279523f4768869074f6c.md" }, { "id": "hm-280bcf235c6d20f33868", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-280bcf235c6d20f33868.json", "report": "/leaderboard/reports/hm-280bcf235c6d20f33868.md", "plan": "/leaderboard/plans/hm-280bcf235c6d20f33868.md" }, { "id": "hm-28ad8cb7b4fb4d83001d", "model_label": "Claude Opus 4.1", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-28ad8cb7b4fb4d83001d.json", "report": "/leaderboard/reports/hm-28ad8cb7b4fb4d83001d.md", "plan": "/leaderboard/plans/hm-28ad8cb7b4fb4d83001d.md" }, { "id": "hm-28b0828888ce75b1c21d", "model_label": "Deepseek R1", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-28b0828888ce75b1c21d.json", "report": "/leaderboard/reports/hm-28b0828888ce75b1c21d.md", "plan": "/leaderboard/plans/hm-28b0828888ce75b1c21d.md" }, { "id": "hm-28b300f97b2de8378133", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-28b300f97b2de8378133.json", "report": "/leaderboard/reports/hm-28b300f97b2de8378133.md", "plan": "/leaderboard/plans/hm-28b300f97b2de8378133.md" }, { "id": "hm-2a2fb401df0b42d7161f", "model_label": "deepseek/deepseek-v4-pro-0813", "lab": "DeepSeek", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2a2fb401df0b42d7161f.json", "report": "/leaderboard/reports/hm-2a2fb401df0b42d7161f.md", "plan": "/leaderboard/plans/hm-2a2fb401df0b42d7161f.md" }, { "id": "hm-2ac5ff0203010b7ab4b5", "model_label": "Kimi k2 Thinking", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2ac5ff0203010b7ab4b5.json", "report": "/leaderboard/reports/hm-2ac5ff0203010b7ab4b5.md", "plan": "/leaderboard/plans/hm-2ac5ff0203010b7ab4b5.md" }, { "id": "hm-2acb346a7adceb7a8246", "model_label": "claude-opus-4-7_xhigh", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2acb346a7adceb7a8246.json", "report": "/leaderboard/reports/hm-2acb346a7adceb7a8246.md", "plan": "/leaderboard/plans/hm-2acb346a7adceb7a8246.md" }, { "id": "hm-2b29a7b5a21e82a2ff04", "model_label": "CohereLabs/c4ai-aya-expanse-8b", "lab": "Cohere", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2b29a7b5a21e82a2ff04.json", "report": "/leaderboard/reports/hm-2b29a7b5a21e82a2ff04.md", "plan": "/leaderboard/plans/hm-2b29a7b5a21e82a2ff04.md" }, { "id": "hm-2b4090ba43ad51fcb345", "model_label": "antgroup/finix_s1_32b", "lab": "Ant Group", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2b4090ba43ad51fcb345.json", "report": "/leaderboard/reports/hm-2b4090ba43ad51fcb345.md", "plan": "/leaderboard/plans/hm-2b4090ba43ad51fcb345.md" }, { "id": "hm-2b9dc2b7266037c8e0e8", "model_label": "Claude 3.5 Haiku", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2b9dc2b7266037c8e0e8.json", "report": "/leaderboard/reports/hm-2b9dc2b7266037c8e0e8.md", "plan": "/leaderboard/plans/hm-2b9dc2b7266037c8e0e8.md" }, { "id": "hm-2c6db42682cc76bbc4a5", "model_label": "gpt-4o-mini-2024-07-18", "lab": "OpenAI", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2c6db42682cc76bbc4a5.json", "report": "/leaderboard/reports/hm-2c6db42682cc76bbc4a5.md", "plan": "/leaderboard/plans/hm-2c6db42682cc76bbc4a5.md" }, { "id": "hm-2c83b811f12deebe7beb", "model_label": "Claude Opus 4.7", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2c83b811f12deebe7beb.json", "report": "/leaderboard/reports/hm-2c83b811f12deebe7beb.md", "plan": "/leaderboard/plans/hm-2c83b811f12deebe7beb.md" }, { "id": "hm-2ce66edd1e7d68c78c41", "model_label": "claude-sonnet-5_xhigh", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2ce66edd1e7d68c78c41.json", "report": "/leaderboard/reports/hm-2ce66edd1e7d68c78c41.md", "plan": "/leaderboard/plans/hm-2ce66edd1e7d68c78c41.md" }, { "id": "hm-2e7a028834a68baf449b", "model_label": "Vicuna-13B", "lab": "LMSYS", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2e7a028834a68baf449b.json", "report": "/leaderboard/reports/hm-2e7a028834a68baf449b.md", "plan": "/leaderboard/plans/hm-2e7a028834a68baf449b.md" }, { "id": "hm-2ee209720f55aea6b18c", "model_label": "Qwen1.5-14B-Chat", "lab": "Alibaba / Qwen", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2ee209720f55aea6b18c.json", "report": "/leaderboard/reports/hm-2ee209720f55aea6b18c.md", "plan": "/leaderboard/plans/hm-2ee209720f55aea6b18c.md" }, { "id": "hm-2f43522c5ec5b9ed5e36", "model_label": "O1", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-2f43522c5ec5b9ed5e36.json", "report": "/leaderboard/reports/hm-2f43522c5ec5b9ed5e36.md", "plan": "/leaderboard/plans/hm-2f43522c5ec5b9ed5e36.md" }, { "id": "hm-307f1278d990a8287981", "model_label": "mistralai/ministral-8b-2410", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-307f1278d990a8287981.json", "report": "/leaderboard/reports/hm-307f1278d990a8287981.md", "plan": "/leaderboard/plans/hm-307f1278d990a8287981.md" }, { "id": "hm-309494a83c86d78f92cb", "model_label": "google/gemini-3.1-flash-lite-preview", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-309494a83c86d78f92cb.json", "report": "/leaderboard/reports/hm-309494a83c86d78f92cb.md", "plan": "/leaderboard/plans/hm-309494a83c86d78f92cb.md" }, { "id": "hm-31385f03c055cab73e75", "model_label": "Claude 3.5 Haiku", "lab": "Anthropic", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-31385f03c055cab73e75.json", "report": "/leaderboard/reports/hm-31385f03c055cab73e75.md", "plan": "/leaderboard/plans/hm-31385f03c055cab73e75.md" }, { "id": "hm-3144995c18a713aaaf31", "model_label": "o4-mini-2025-04-16_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3144995c18a713aaaf31.json", "report": "/leaderboard/reports/hm-3144995c18a713aaaf31.md", "plan": "/leaderboard/plans/hm-3144995c18a713aaaf31.md" }, { "id": "hm-31b2c8a0237b9bd6eaf1", "model_label": "GPT-3.5 Turbo", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-31b2c8a0237b9bd6eaf1.json", "report": "/leaderboard/reports/hm-31b2c8a0237b9bd6eaf1.md", "plan": "/leaderboard/plans/hm-31b2c8a0237b9bd6eaf1.md" }, { "id": "hm-31c8886a56d7717c7c0d", "model_label": "kimi-k2.6", "lab": "Moonshot", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-31c8886a56d7717c7c0d.json", "report": "/leaderboard/reports/hm-31c8886a56d7717c7c0d.md", "plan": "/leaderboard/plans/hm-31c8886a56d7717c7c0d.md" }, { "id": "hm-3260c579105ebfc23f00", "model_label": "amazon/nova-lite-v1:0", "lab": "Amazon", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3260c579105ebfc23f00.json", "report": "/leaderboard/reports/hm-3260c579105ebfc23f00.md", "plan": "/leaderboard/plans/hm-3260c579105ebfc23f00.md" }, { "id": "hm-32bf9d4c740557b7b379", "model_label": "glm-5.2_max", "lab": "Z.ai (Zhipu AI)", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-32bf9d4c740557b7b379.json", "report": "/leaderboard/reports/hm-32bf9d4c740557b7b379.md", "plan": "/leaderboard/plans/hm-32bf9d4c740557b7b379.md" }, { "id": "hm-3492381fa22c20be460d", "model_label": "gemini-3-flash-preview_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3492381fa22c20be460d.json", "report": "/leaderboard/reports/hm-3492381fa22c20be460d.md", "plan": "/leaderboard/plans/hm-3492381fa22c20be460d.md" }, { "id": "hm-349c38ab13133292ac90", "model_label": "anthropic/claude-opus-4-20250514", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-349c38ab13133292ac90.json", "report": "/leaderboard/reports/hm-349c38ab13133292ac90.md", "plan": "/leaderboard/plans/hm-349c38ab13133292ac90.md" }, { "id": "hm-3504155926a8d32f5776", "model_label": "llama-32-1b-instruct", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3504155926a8d32f5776.json", "report": "/leaderboard/reports/hm-3504155926a8d32f5776.md", "plan": "/leaderboard/plans/hm-3504155926a8d32f5776.md" }, { "id": "hm-359407c30dc7fc58765b", "model_label": "GPT-4o", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-359407c30dc7fc58765b.json", "report": "/leaderboard/reports/hm-359407c30dc7fc58765b.md", "plan": "/leaderboard/plans/hm-359407c30dc7fc58765b.md" }, { "id": "hm-37262500108c033d9bd7", "model_label": "GPT-5 Nano", "lab": "OpenAI", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-37262500108c033d9bd7.json", "report": "/leaderboard/reports/hm-37262500108c033d9bd7.md", "plan": "/leaderboard/plans/hm-37262500108c033d9bd7.md" }, { "id": "hm-38bd8751ee87ebd427bf", "model_label": "qwen15-32b-chat", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-38bd8751ee87ebd427bf.json", "report": "/leaderboard/reports/hm-38bd8751ee87ebd427bf.md", "plan": "/leaderboard/plans/hm-38bd8751ee87ebd427bf.md" }, { "id": "hm-38cac6705e7075a2c8b9", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-38cac6705e7075a2c8b9.json", "report": "/leaderboard/reports/hm-38cac6705e7075a2c8b9.md", "plan": "/leaderboard/plans/hm-38cac6705e7075a2c8b9.md" }, { "id": "hm-38ec66165fcf5bf625b3", "model_label": "Claude 4.5 Sonnet", "lab": "Anthropic", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-38ec66165fcf5bf625b3.json", "report": "/leaderboard/reports/hm-38ec66165fcf5bf625b3.md", "plan": "/leaderboard/plans/hm-38ec66165fcf5bf625b3.md" }, { "id": "hm-391f32e207c380c2caed", "model_label": "claude-fable-5_xhigh", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-391f32e207c380c2caed.json", "report": "/leaderboard/reports/hm-391f32e207c380c2caed.md", "plan": "/leaderboard/plans/hm-391f32e207c380c2caed.md" }, { "id": "hm-392eef39535fc2372724", "model_label": "qwen25-15b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-392eef39535fc2372724.json", "report": "/leaderboard/reports/hm-392eef39535fc2372724.md", "plan": "/leaderboard/plans/hm-392eef39535fc2372724.md" }, { "id": "hm-3a02aa296f5a8131fb74", "model_label": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "lab": "Meta", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3a02aa296f5a8131fb74.json", "report": "/leaderboard/reports/hm-3a02aa296f5a8131fb74.md", "plan": "/leaderboard/plans/hm-3a02aa296f5a8131fb74.md" }, { "id": "hm-3b4d83473be8d2f3b653", "model_label": "Grok-4", "lab": "xAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3b4d83473be8d2f3b653.json", "report": "/leaderboard/reports/hm-3b4d83473be8d2f3b653.md", "plan": "/leaderboard/plans/hm-3b4d83473be8d2f3b653.md" }, { "id": "hm-3db41a383b8bcd3d14ba", "model_label": "o4-mini", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3db41a383b8bcd3d14ba.json", "report": "/leaderboard/reports/hm-3db41a383b8bcd3d14ba.md", "plan": "/leaderboard/plans/hm-3db41a383b8bcd3d14ba.md" }, { "id": "hm-3efa353db382710d2c3a", "model_label": "o3-mini-2025-01-31_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3efa353db382710d2c3a.json", "report": "/leaderboard/reports/hm-3efa353db382710d2c3a.md", "plan": "/leaderboard/plans/hm-3efa353db382710d2c3a.md" }, { "id": "hm-3f68287714f7077e4b7c", "model_label": "anthropic/claude-sonnet-4-20250514", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3f68287714f7077e4b7c.json", "report": "/leaderboard/reports/hm-3f68287714f7077e4b7c.md", "plan": "/leaderboard/plans/hm-3f68287714f7077e4b7c.md" }, { "id": "hm-3fea97c369eac014a16e", "model_label": "o3-mini-low", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-3fea97c369eac014a16e.json", "report": "/leaderboard/reports/hm-3fea97c369eac014a16e.md", "plan": "/leaderboard/plans/hm-3fea97c369eac014a16e.md" }, { "id": "hm-40b42cf12e0bd22f6b36", "model_label": "Grok-4", "lab": "xAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-40b42cf12e0bd22f6b36.json", "report": "/leaderboard/reports/hm-40b42cf12e0bd22f6b36.md", "plan": "/leaderboard/plans/hm-40b42cf12e0bd22f6b36.md" }, { "id": "hm-429dd772fe154108607a", "model_label": "llama-2-70b-chat", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-429dd772fe154108607a.json", "report": "/leaderboard/reports/hm-429dd772fe154108607a.md", "plan": "/leaderboard/plans/hm-429dd772fe154108607a.md" }, { "id": "hm-42d13b20582d5c0f91a9", "model_label": "S1.1 32B", "lab": "simplescaling", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-42d13b20582d5c0f91a9.json", "report": "/leaderboard/reports/hm-42d13b20582d5c0f91a9.md", "plan": "/leaderboard/plans/hm-42d13b20582d5c0f91a9.md" }, { "id": "hm-432208434eed0bf56df4", "model_label": "qwen3.8-max-0902_xhigh", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-432208434eed0bf56df4.json", "report": "/leaderboard/reports/hm-432208434eed0bf56df4.md", "plan": "/leaderboard/plans/hm-432208434eed0bf56df4.md" }, { "id": "hm-43f2d98ef13727adecdd", "model_label": "GPT-5 mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-43f2d98ef13727adecdd.json", "report": "/leaderboard/reports/hm-43f2d98ef13727adecdd.md", "plan": "/leaderboard/plans/hm-43f2d98ef13727adecdd.md" }, { "id": "hm-4461e4eac4f52167dc93", "model_label": "GPT-5.2 (medium)", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4461e4eac4f52167dc93.json", "report": "/leaderboard/reports/hm-4461e4eac4f52167dc93.md", "plan": "/leaderboard/plans/hm-4461e4eac4f52167dc93.md" }, { "id": "hm-447dacde7536389f8538", "model_label": "o4-mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-447dacde7536389f8538.json", "report": "/leaderboard/reports/hm-447dacde7536389f8538.md", "plan": "/leaderboard/plans/hm-447dacde7536389f8538.md" }, { "id": "hm-44d1c0a74c95d292134f", "model_label": "gpt-5-2025-08-07_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-44d1c0a74c95d292134f.json", "report": "/leaderboard/reports/hm-44d1c0a74c95d292134f.md", "plan": "/leaderboard/plans/hm-44d1c0a74c95d292134f.md" }, { "id": "hm-457125edad40ccabcdf5", "model_label": "Deepseek R1", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-457125edad40ccabcdf5.json", "report": "/leaderboard/reports/hm-457125edad40ccabcdf5.md", "plan": "/leaderboard/plans/hm-457125edad40ccabcdf5.md" }, { "id": "hm-459afd4bced8fac68c42", "model_label": "GPT-5.2", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-459afd4bced8fac68c42.json", "report": "/leaderboard/reports/hm-459afd4bced8fac68c42.md", "plan": "/leaderboard/plans/hm-459afd4bced8fac68c42.md" }, { "id": "hm-4797fedbde239f133caa", "model_label": "mistralai/ministral-3-14b-2512", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4797fedbde239f133caa.json", "report": "/leaderboard/reports/hm-4797fedbde239f133caa.md", "plan": "/leaderboard/plans/hm-4797fedbde239f133caa.md" }, { "id": "hm-4884cd85c9f0208e53a1", "model_label": "gpt-4.1-2025-04-14", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4884cd85c9f0208e53a1.json", "report": "/leaderboard/reports/hm-4884cd85c9f0208e53a1.md", "plan": "/leaderboard/plans/hm-4884cd85c9f0208e53a1.md" }, { "id": "hm-4a743ec5b7d62fc93678", "model_label": "qwen/qwen3.5-flash-2026-02-23", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4a743ec5b7d62fc93678.json", "report": "/leaderboard/reports/hm-4a743ec5b7d62fc93678.md", "plan": "/leaderboard/plans/hm-4a743ec5b7d62fc93678.md" }, { "id": "hm-4be6a765baa656f16d0f", "model_label": "Command R", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4be6a765baa656f16d0f.json", "report": "/leaderboard/reports/hm-4be6a765baa656f16d0f.md", "plan": "/leaderboard/plans/hm-4be6a765baa656f16d0f.md" }, { "id": "hm-4bfd76004053df44e611", "model_label": "Claude 4.1 Opus", "lab": "Anthropic", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4bfd76004053df44e611.json", "report": "/leaderboard/reports/hm-4bfd76004053df44e611.md", "plan": "/leaderboard/plans/hm-4bfd76004053df44e611.md" }, { "id": "hm-4c07722b910bab7ff7b4", "model_label": "claude-sonnet-4-6_high", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4c07722b910bab7ff7b4.json", "report": "/leaderboard/reports/hm-4c07722b910bab7ff7b4.md", "plan": "/leaderboard/plans/hm-4c07722b910bab7ff7b4.md" }, { "id": "hm-4c97c9d948d0cea7b712", "model_label": "DeepSeek R1 0528", "lab": "DeepSeek", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4c97c9d948d0cea7b712.json", "report": "/leaderboard/reports/hm-4c97c9d948d0cea7b712.md", "plan": "/leaderboard/plans/hm-4c97c9d948d0cea7b712.md" }, { "id": "hm-4c9f54336d02d49f38f7", "model_label": "muse-spark-1.2_xhigh", "lab": "Meta AI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4c9f54336d02d49f38f7.json", "report": "/leaderboard/reports/hm-4c9f54336d02d49f38f7.md", "plan": "/leaderboard/plans/hm-4c9f54336d02d49f38f7.md" }, { "id": "hm-4d2f0f18dfc69a8b3e03", "model_label": "Mixtral (8x22B)", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4d2f0f18dfc69a8b3e03.json", "report": "/leaderboard/reports/hm-4d2f0f18dfc69a8b3e03.md", "plan": "/leaderboard/plans/hm-4d2f0f18dfc69a8b3e03.md" }, { "id": "hm-4d974d10040671c37245", "model_label": "gpt-4.1-mini-2025-04-14", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4d974d10040671c37245.json", "report": "/leaderboard/reports/hm-4d974d10040671c37245.md", "plan": "/leaderboard/plans/hm-4d974d10040671c37245.md" }, { "id": "hm-4e49d8d16317188c8297", "model_label": "claude-haiku-5-5_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4e49d8d16317188c8297.json", "report": "/leaderboard/reports/hm-4e49d8d16317188c8297.md", "plan": "/leaderboard/plans/hm-4e49d8d16317188c8297.md" }, { "id": "hm-4f1af506b53195966888", "model_label": "Llama 4 Maverick", "lab": "Meta", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-4f1af506b53195966888.json", "report": "/leaderboard/reports/hm-4f1af506b53195966888.md", "plan": "/leaderboard/plans/hm-4f1af506b53195966888.md" }, { "id": "hm-503d8b0c8548aec90f65", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-503d8b0c8548aec90f65.json", "report": "/leaderboard/reports/hm-503d8b0c8548aec90f65.md", "plan": "/leaderboard/plans/hm-503d8b0c8548aec90f65.md" }, { "id": "hm-50462725b7fe15092c49", "model_label": "grok-4.6_high", "lab": "xAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-50462725b7fe15092c49.json", "report": "/leaderboard/reports/hm-50462725b7fe15092c49.md", "plan": "/leaderboard/plans/hm-50462725b7fe15092c49.md" }, { "id": "hm-50a3473da4f81481e6a3", "model_label": "Llama 3.1 70B Tulu 3 DPO", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-50a3473da4f81481e6a3.json", "report": "/leaderboard/reports/hm-50a3473da4f81481e6a3.md", "plan": "/leaderboard/plans/hm-50a3473da4f81481e6a3.md" }, { "id": "hm-51af8e9a32ed11670e42", "model_label": "Llama-3.1-70B-Instruct", "lab": "Meta", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-51af8e9a32ed11670e42.json", "report": "/leaderboard/reports/hm-51af8e9a32ed11670e42.md", "plan": "/leaderboard/plans/hm-51af8e9a32ed11670e42.md" }, { "id": "hm-51cfec39319f303614df", "model_label": "zai-org/glm-5", "lab": "Z.ai", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-51cfec39319f303614df.json", "report": "/leaderboard/reports/hm-51cfec39319f303614df.md", "plan": "/leaderboard/plans/hm-51cfec39319f303614df.md" }, { "id": "hm-520713b6dca17e90cf0f", "model_label": "GPT-5 High", "lab": "OpenAI", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-520713b6dca17e90cf0f.json", "report": "/leaderboard/reports/hm-520713b6dca17e90cf0f.md", "plan": "/leaderboard/plans/hm-520713b6dca17e90cf0f.md" }, { "id": "hm-5338ddf2fdcabec41c83", "model_label": "o1", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5338ddf2fdcabec41c83.json", "report": "/leaderboard/reports/hm-5338ddf2fdcabec41c83.md", "plan": "/leaderboard/plans/hm-5338ddf2fdcabec41c83.md" }, { "id": "hm-54fad731632176848a5d", "model_label": "Llama 3.1 405B Instruct", "lab": "Meta", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-54fad731632176848a5d.json", "report": "/leaderboard/reports/hm-54fad731632176848a5d.md", "plan": "/leaderboard/plans/hm-54fad731632176848a5d.md" }, { "id": "hm-568180fae536de3f4af9", "model_label": "Llama 3.1 8B Base", "lab": "Meta", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-568180fae536de3f4af9.json", "report": "/leaderboard/reports/hm-568180fae536de3f4af9.md", "plan": "/leaderboard/plans/hm-568180fae536de3f4af9.md" }, { "id": "hm-56c60f81ae23f1350a88", "model_label": "Llama 3.1 8B Tulu 3 DPO", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-56c60f81ae23f1350a88.json", "report": "/leaderboard/reports/hm-56c60f81ae23f1350a88.md", "plan": "/leaderboard/plans/hm-56c60f81ae23f1350a88.md" }, { "id": "hm-56ffd20926f1067fff44", "model_label": "muse-spark-1.1", "lab": "Meta AI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-56ffd20926f1067fff44.json", "report": "/leaderboard/reports/hm-56ffd20926f1067fff44.md", "plan": "/leaderboard/plans/hm-56ffd20926f1067fff44.md" }, { "id": "hm-572361de4848eac79ae9", "model_label": "zai-org/GLM-4.7-flash", "lab": "Z.ai", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-572361de4848eac79ae9.json", "report": "/leaderboard/reports/hm-572361de4848eac79ae9.md", "plan": "/leaderboard/plans/hm-572361de4848eac79ae9.md" }, { "id": "hm-5789d3d9d7e4ebc2d81d", "model_label": "Claude 3.5 Sonnet", "lab": "Anthropic", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5789d3d9d7e4ebc2d81d.json", "report": "/leaderboard/reports/hm-5789d3d9d7e4ebc2d81d.md", "plan": "/leaderboard/plans/hm-5789d3d9d7e4ebc2d81d.md" }, { "id": "hm-589dc8162fce433269f0", "model_label": "Gemini 1.5 Flash", "lab": "Google", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-589dc8162fce433269f0.json", "report": "/leaderboard/reports/hm-589dc8162fce433269f0.md", "plan": "/leaderboard/plans/hm-589dc8162fce433269f0.md" }, { "id": "hm-58c23c3324c77614c5be", "model_label": "Llama 3.1 8B Tulu 3 SFT", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-58c23c3324c77614c5be.json", "report": "/leaderboard/reports/hm-58c23c3324c77614c5be.md", "plan": "/leaderboard/plans/hm-58c23c3324c77614c5be.md" }, { "id": "hm-5931df28b1d2792640e9", "model_label": "Claude Opus 4.1", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5931df28b1d2792640e9.json", "report": "/leaderboard/reports/hm-5931df28b1d2792640e9.md", "plan": "/leaderboard/plans/hm-5931df28b1d2792640e9.md" }, { "id": "hm-5aed15709c6bc6f5d743", "model_label": "llama-31-405b-instruct", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5aed15709c6bc6f5d743.json", "report": "/leaderboard/reports/hm-5aed15709c6bc6f5d743.md", "plan": "/leaderboard/plans/hm-5aed15709c6bc6f5d743.md" }, { "id": "hm-5bc9d118c93c163892e7", "model_label": "openai/gpt-4.1-2025-04-14", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5bc9d118c93c163892e7.json", "report": "/leaderboard/reports/hm-5bc9d118c93c163892e7.md", "plan": "/leaderboard/plans/hm-5bc9d118c93c163892e7.md" }, { "id": "hm-5bf558c275f39f79cb74", "model_label": "Llama 3.3 70B Instruct", "lab": "Meta", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5bf558c275f39f79cb74.json", "report": "/leaderboard/reports/hm-5bf558c275f39f79cb74.md", "plan": "/leaderboard/plans/hm-5bf558c275f39f79cb74.md" }, { "id": "hm-5c023a0ed12012ac4359", "model_label": "google/gemma-3-4b-it", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5c023a0ed12012ac4359.json", "report": "/leaderboard/reports/hm-5c023a0ed12012ac4359.md", "plan": "/leaderboard/plans/hm-5c023a0ed12012ac4359.md" }, { "id": "hm-5d3c1d41eddf18677343", "model_label": "qwen25-32b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5d3c1d41eddf18677343.json", "report": "/leaderboard/reports/hm-5d3c1d41eddf18677343.md", "plan": "/leaderboard/plans/hm-5d3c1d41eddf18677343.md" }, { "id": "hm-5e054a81bbd917850d69", "model_label": "Claude Sonnet 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5e054a81bbd917850d69.json", "report": "/leaderboard/reports/hm-5e054a81bbd917850d69.md", "plan": "/leaderboard/plans/hm-5e054a81bbd917850d69.md" }, { "id": "hm-5e417905f1e5b268a159", "model_label": "openai/gpt-5-nano-2025-08-07", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5e417905f1e5b268a159.json", "report": "/leaderboard/reports/hm-5e417905f1e5b268a159.md", "plan": "/leaderboard/plans/hm-5e417905f1e5b268a159.md" }, { "id": "hm-5eb2256949bc1bdd1cc1", "model_label": "gpt-6-astra_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5eb2256949bc1bdd1cc1.json", "report": "/leaderboard/reports/hm-5eb2256949bc1bdd1cc1.md", "plan": "/leaderboard/plans/hm-5eb2256949bc1bdd1cc1.md" }, { "id": "hm-5eddbced786b136e2201", "model_label": "claude-opus-4-5-20251101_32K", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5eddbced786b136e2201.json", "report": "/leaderboard/reports/hm-5eddbced786b136e2201.md", "plan": "/leaderboard/plans/hm-5eddbced786b136e2201.md" }, { "id": "hm-5ee7a42d5cd0c41a0f8c", "model_label": "deepseek-ai/DeepSeek-V3.2-Exp", "lab": "DeepSeek", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5ee7a42d5cd0c41a0f8c.json", "report": "/leaderboard/reports/hm-5ee7a42d5cd0c41a0f8c.md", "plan": "/leaderboard/plans/hm-5ee7a42d5cd0c41a0f8c.md" }, { "id": "hm-5f1f644808b0c7d4b626", "model_label": "openai/gpt-4o-2024-08-06", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5f1f644808b0c7d4b626.json", "report": "/leaderboard/reports/hm-5f1f644808b0c7d4b626.md", "plan": "/leaderboard/plans/hm-5f1f644808b0c7d4b626.md" }, { "id": "hm-5f7d05f36b24bbfc6ea0", "model_label": "gpt-4o-2024-11-20", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5f7d05f36b24bbfc6ea0.json", "report": "/leaderboard/reports/hm-5f7d05f36b24bbfc6ea0.md", "plan": "/leaderboard/plans/hm-5f7d05f36b24bbfc6ea0.md" }, { "id": "hm-5fa042d6076d6f5ff861", "model_label": "Kimi K2 0905", "lab": "Moonshot AI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-5fa042d6076d6f5ff861.json", "report": "/leaderboard/reports/hm-5fa042d6076d6f5ff861.md", "plan": "/leaderboard/plans/hm-5fa042d6076d6f5ff861.md" }, { "id": "hm-602c8a1a28eaa727bbfc", "model_label": "GPT-OSS-120B", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-602c8a1a28eaa727bbfc.json", "report": "/leaderboard/reports/hm-602c8a1a28eaa727bbfc.md", "plan": "/leaderboard/plans/hm-602c8a1a28eaa727bbfc.md" }, { "id": "hm-602f06562b57b59ad4ec", "model_label": "google/gemini-3-pro-preview", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-602f06562b57b59ad4ec.json", "report": "/leaderboard/reports/hm-602f06562b57b59ad4ec.md", "plan": "/leaderboard/plans/hm-602f06562b57b59ad4ec.md" }, { "id": "hm-61bcb78b2cc91b677b14", "model_label": "Gemini 3.5 Flash", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-61bcb78b2cc91b677b14.json", "report": "/leaderboard/reports/hm-61bcb78b2cc91b677b14.md", "plan": "/leaderboard/plans/hm-61bcb78b2cc91b677b14.md" }, { "id": "hm-61daf29d662f8a3e85f9", "model_label": "xai-org/grok-4-fast-reasoning", "lab": "xAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-61daf29d662f8a3e85f9.json", "report": "/leaderboard/reports/hm-61daf29d662f8a3e85f9.md", "plan": "/leaderboard/plans/hm-61daf29d662f8a3e85f9.md" }, { "id": "hm-61f1d3decb0c143ad00e", "model_label": "Alpaca-7B", "lab": "Stanford CRFM", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-61f1d3decb0c143ad00e.json", "report": "/leaderboard/reports/hm-61f1d3decb0c143ad00e.md", "plan": "/leaderboard/plans/hm-61f1d3decb0c143ad00e.md" }, { "id": "hm-62767e6130d0b2bbb7d4", "model_label": "Claude-3 Haiku", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-62767e6130d0b2bbb7d4.json", "report": "/leaderboard/reports/hm-62767e6130d0b2bbb7d4.md", "plan": "/leaderboard/plans/hm-62767e6130d0b2bbb7d4.md" }, { "id": "hm-645ad45aa61215c07c74", "model_label": "claude-fable-5-1_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-645ad45aa61215c07c74.json", "report": "/leaderboard/reports/hm-645ad45aa61215c07c74.md", "plan": "/leaderboard/plans/hm-645ad45aa61215c07c74.md" }, { "id": "hm-64a4f8985751b9272945", "model_label": "grok-2-1212", "lab": "xAI", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-64a4f8985751b9272945.json", "report": "/leaderboard/reports/hm-64a4f8985751b9272945.md", "plan": "/leaderboard/plans/hm-64a4f8985751b9272945.md" }, { "id": "hm-64c0c8c54e1ad8aa31a3", "model_label": "gemma-2-9b-it", "lab": "Google", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-64c0c8c54e1ad8aa31a3.json", "report": "/leaderboard/reports/hm-64c0c8c54e1ad8aa31a3.md", "plan": "/leaderboard/plans/hm-64c0c8c54e1ad8aa31a3.md" }, { "id": "hm-64ee0f927479cf138c35", "model_label": "openai/gpt-5.2-low-2025-12-11", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-64ee0f927479cf138c35.json", "report": "/leaderboard/reports/hm-64ee0f927479cf138c35.md", "plan": "/leaderboard/plans/hm-64ee0f927479cf138c35.md" }, { "id": "hm-6518d434b135bcdc2d3a", "model_label": "Claude Sonnet 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6518d434b135bcdc2d3a.json", "report": "/leaderboard/reports/hm-6518d434b135bcdc2d3a.md", "plan": "/leaderboard/plans/hm-6518d434b135bcdc2d3a.md" }, { "id": "hm-65901c38f8da87490746", "model_label": "GPT-J 6B", "lab": "EleutherAI", "source": "truthfulqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-65901c38f8da87490746.json", "report": "/leaderboard/reports/hm-65901c38f8da87490746.md", "plan": "/leaderboard/plans/hm-65901c38f8da87490746.md" }, { "id": "hm-659145b1b067a21aadb6", "model_label": "GPT-5", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-659145b1b067a21aadb6.json", "report": "/leaderboard/reports/hm-659145b1b067a21aadb6.md", "plan": "/leaderboard/plans/hm-659145b1b067a21aadb6.md" }, { "id": "hm-6600ca05ed2419c4c870", "model_label": "gemini-2.0-flash", "lab": "Google", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6600ca05ed2419c4c870.json", "report": "/leaderboard/reports/hm-6600ca05ed2419c4c870.md", "plan": "/leaderboard/plans/hm-6600ca05ed2419c4c870.md" }, { "id": "hm-66807e3ff67d354d5705", "model_label": "Deepseek R1", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-66807e3ff67d354d5705.json", "report": "/leaderboard/reports/hm-66807e3ff67d354d5705.md", "plan": "/leaderboard/plans/hm-66807e3ff67d354d5705.md" }, { "id": "hm-67b3142fe3af6a6f73ec", "model_label": "qwen3.7-max", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-67b3142fe3af6a6f73ec.json", "report": "/leaderboard/reports/hm-67b3142fe3af6a6f73ec.md", "plan": "/leaderboard/plans/hm-67b3142fe3af6a6f73ec.md" }, { "id": "hm-689cf6441798cbbcdeb3", "model_label": "GPT-4 Turbo", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-689cf6441798cbbcdeb3.json", "report": "/leaderboard/reports/hm-689cf6441798cbbcdeb3.md", "plan": "/leaderboard/plans/hm-689cf6441798cbbcdeb3.md" }, { "id": "hm-6948daaf005b5b212111", "model_label": "google/gemini-3.1-pro-preview", "lab": "Google", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6948daaf005b5b212111.json", "report": "/leaderboard/reports/hm-6948daaf005b5b212111.md", "plan": "/leaderboard/plans/hm-6948daaf005b5b212111.md" }, { "id": "hm-69dc3ffcc36e35d94293", "model_label": "gpt-5.2-2025-12-11_xhigh", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-69dc3ffcc36e35d94293.json", "report": "/leaderboard/reports/hm-69dc3ffcc36e35d94293.md", "plan": "/leaderboard/plans/hm-69dc3ffcc36e35d94293.md" }, { "id": "hm-6bd328082ca0eba06d06", "model_label": "qwen25-72b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6bd328082ca0eba06d06.json", "report": "/leaderboard/reports/hm-6bd328082ca0eba06d06.md", "plan": "/leaderboard/plans/hm-6bd328082ca0eba06d06.md" }, { "id": "hm-6be17c5a8bc624c54a4b", "model_label": "GPT-5.5", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6be17c5a8bc624c54a4b.json", "report": "/leaderboard/reports/hm-6be17c5a8bc624c54a4b.md", "plan": "/leaderboard/plans/hm-6be17c5a8bc624c54a4b.md" }, { "id": "hm-6c5136aec0877247cae5", "model_label": "Qwen3 235B A22B 2507", "lab": "Alibaba", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6c5136aec0877247cae5.json", "report": "/leaderboard/reports/hm-6c5136aec0877247cae5.md", "plan": "/leaderboard/plans/hm-6c5136aec0877247cae5.md" }, { "id": "hm-6c5b30bf2b5aca110172", "model_label": "Claude Sonnet 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6c5b30bf2b5aca110172.json", "report": "/leaderboard/reports/hm-6c5b30bf2b5aca110172.md", "plan": "/leaderboard/plans/hm-6c5b30bf2b5aca110172.md" }, { "id": "hm-6cdfa9c95a011b8db1b7", "model_label": "Command R", "lab": "Cohere", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6cdfa9c95a011b8db1b7.json", "report": "/leaderboard/reports/hm-6cdfa9c95a011b8db1b7.md", "plan": "/leaderboard/plans/hm-6cdfa9c95a011b8db1b7.md" }, { "id": "hm-6cee82beaadbc379f8d2", "model_label": "GPT-4o", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6cee82beaadbc379f8d2.json", "report": "/leaderboard/reports/hm-6cee82beaadbc379f8d2.md", "plan": "/leaderboard/plans/hm-6cee82beaadbc379f8d2.md" }, { "id": "hm-6d651493e476ee6a7fdf", "model_label": "qwen/qwen3.5-plus-2026-02-15", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6d651493e476ee6a7fdf.json", "report": "/leaderboard/reports/hm-6d651493e476ee6a7fdf.md", "plan": "/leaderboard/plans/hm-6d651493e476ee6a7fdf.md" }, { "id": "hm-6e022e89114a5b6ecacd", "model_label": "gpt-4-turbo-2024-04-09", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6e022e89114a5b6ecacd.json", "report": "/leaderboard/reports/hm-6e022e89114a5b6ecacd.md", "plan": "/leaderboard/plans/hm-6e022e89114a5b6ecacd.md" }, { "id": "hm-6ef7ee95424d1a149e10", "model_label": "google/gemma-3-27b-it", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-6ef7ee95424d1a149e10.json", "report": "/leaderboard/reports/hm-6ef7ee95424d1a149e10.md", "plan": "/leaderboard/plans/hm-6ef7ee95424d1a149e10.md" }, { "id": "hm-71a68ac1e26f62ea14c0", "model_label": "glm-5.3_max", "lab": "Z.ai (Zhipu AI)", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-71a68ac1e26f62ea14c0.json", "report": "/leaderboard/reports/hm-71a68ac1e26f62ea14c0.md", "plan": "/leaderboard/plans/hm-71a68ac1e26f62ea14c0.md" }, { "id": "hm-71d4f4559d7992ab13e3", "model_label": "anthropic/claude-opus-5.5", "lab": "Anthropic", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-71d4f4559d7992ab13e3.json", "report": "/leaderboard/reports/hm-71d4f4559d7992ab13e3.md", "plan": "/leaderboard/plans/hm-71d4f4559d7992ab13e3.md" }, { "id": "hm-71dd528c2544622a7b05", "model_label": "microsoft/Phi-4", "lab": "Microsoft", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-71dd528c2544622a7b05.json", "report": "/leaderboard/reports/hm-71dd528c2544622a7b05.md", "plan": "/leaderboard/plans/hm-71dd528c2544622a7b05.md" }, { "id": "hm-724f5507e1f258ffc91a", "model_label": "o3-low", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-724f5507e1f258ffc91a.json", "report": "/leaderboard/reports/hm-724f5507e1f258ffc91a.md", "plan": "/leaderboard/plans/hm-724f5507e1f258ffc91a.md" }, { "id": "hm-728f089ce3a80cbf6516", "model_label": "Gemini 2.5 Flash", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-728f089ce3a80cbf6516.json", "report": "/leaderboard/reports/hm-728f089ce3a80cbf6516.md", "plan": "/leaderboard/plans/hm-728f089ce3a80cbf6516.md" }, { "id": "hm-72a910138d463a6f0cbe", "model_label": "o4-mini-2025-04-16_low", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-72a910138d463a6f0cbe.json", "report": "/leaderboard/reports/hm-72a910138d463a6f0cbe.md", "plan": "/leaderboard/plans/hm-72a910138d463a6f0cbe.md" }, { "id": "hm-72e20b1bbd460d7d70af", "model_label": "gemini-3.8-flash_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-72e20b1bbd460d7d70af.json", "report": "/leaderboard/reports/hm-72e20b1bbd460d7d70af.md", "plan": "/leaderboard/plans/hm-72e20b1bbd460d7d70af.md" }, { "id": "hm-734ebe8a3c0d5015b20a", "model_label": "mistralai/mistral-small-2501", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-734ebe8a3c0d5015b20a.json", "report": "/leaderboard/reports/hm-734ebe8a3c0d5015b20a.md", "plan": "/leaderboard/plans/hm-734ebe8a3c0d5015b20a.md" }, { "id": "hm-73721ae1b64f8428fb33", "model_label": "Llama-3-8B-Instruct", "lab": "Meta", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-73721ae1b64f8428fb33.json", "report": "/leaderboard/reports/hm-73721ae1b64f8428fb33.md", "plan": "/leaderboard/plans/hm-73721ae1b64f8428fb33.md" }, { "id": "hm-7379540205d47c60939c", "model_label": "gpt-6-luna_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7379540205d47c60939c.json", "report": "/leaderboard/reports/hm-7379540205d47c60939c.md", "plan": "/leaderboard/plans/hm-7379540205d47c60939c.md" }, { "id": "hm-737e1cbf9e13a3729852", "model_label": "Claude-3 Sonnet", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-737e1cbf9e13a3729852.json", "report": "/leaderboard/reports/hm-737e1cbf9e13a3729852.md", "plan": "/leaderboard/plans/hm-737e1cbf9e13a3729852.md" }, { "id": "hm-73a85fe74abeb0f181d5", "model_label": "o4-mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-73a85fe74abeb0f181d5.json", "report": "/leaderboard/reports/hm-73a85fe74abeb0f181d5.md", "plan": "/leaderboard/plans/hm-73a85fe74abeb0f181d5.md" }, { "id": "hm-73bfea6a7b7fd492c731", "model_label": "OpenAI o1-preview", "lab": "OpenAI", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-73bfea6a7b7fd492c731.json", "report": "/leaderboard/reports/hm-73bfea6a7b7fd492c731.md", "plan": "/leaderboard/plans/hm-73bfea6a7b7fd492c731.md" }, { "id": "hm-73dbde0fd0a7b0cf96dd", "model_label": "gpt-4.1-nano-2025-04-14", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-73dbde0fd0a7b0cf96dd.json", "report": "/leaderboard/reports/hm-73dbde0fd0a7b0cf96dd.md", "plan": "/leaderboard/plans/hm-73dbde0fd0a7b0cf96dd.md" }, { "id": "hm-73dc12fafcd7d9d723a7", "model_label": "o3-mini", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-73dc12fafcd7d9d723a7.json", "report": "/leaderboard/reports/hm-73dc12fafcd7d9d723a7.md", "plan": "/leaderboard/plans/hm-73dc12fafcd7d9d723a7.md" }, { "id": "hm-75783bf435f1d7a25b96", "model_label": "GPT-4o Mini", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-75783bf435f1d7a25b96.json", "report": "/leaderboard/reports/hm-75783bf435f1d7a25b96.md", "plan": "/leaderboard/plans/hm-75783bf435f1d7a25b96.md" }, { "id": "hm-75d150c5a0ecc3197956", "model_label": "LLaMA-7B", "lab": "Meta", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-75d150c5a0ecc3197956.json", "report": "/leaderboard/reports/hm-75d150c5a0ecc3197956.md", "plan": "/leaderboard/plans/hm-75d150c5a0ecc3197956.md" }, { "id": "hm-76ac46f9322febd9b62b", "model_label": "Claude Sonnet 4.5", "lab": "Anthropic", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-76ac46f9322febd9b62b.json", "report": "/leaderboard/reports/hm-76ac46f9322febd9b62b.md", "plan": "/leaderboard/plans/hm-76ac46f9322febd9b62b.md" }, { "id": "hm-76bc3912c39e3a185b30", "model_label": "mistral-large-4-0_high", "lab": "Mistral AI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-76bc3912c39e3a185b30.json", "report": "/leaderboard/reports/hm-76bc3912c39e3a185b30.md", "plan": "/leaderboard/plans/hm-76bc3912c39e3a185b30.md" }, { "id": "hm-77336b1e12cd4ca22406", "model_label": "Mistral-7B-Instruct-v0.2", "lab": "Mistral AI", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-77336b1e12cd4ca22406.json", "report": "/leaderboard/reports/hm-77336b1e12cd4ca22406.md", "plan": "/leaderboard/plans/hm-77336b1e12cd4ca22406.md" }, { "id": "hm-77368e995527acad6cac", "model_label": "deepseek-ai/DeepSeek-R1", "lab": "DeepSeek", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-77368e995527acad6cac.json", "report": "/leaderboard/reports/hm-77368e995527acad6cac.md", "plan": "/leaderboard/plans/hm-77368e995527acad6cac.md" }, { "id": "hm-78eabb4cce1941aaaf68", "model_label": "openai/gpt-5.4-2026-03-05", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-78eabb4cce1941aaaf68.json", "report": "/leaderboard/reports/hm-78eabb4cce1941aaaf68.md", "plan": "/leaderboard/plans/hm-78eabb4cce1941aaaf68.md" }, { "id": "hm-791844f7ebdacba890a4", "model_label": "llama3-70b-instruct", "lab": "Meta", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-791844f7ebdacba890a4.json", "report": "/leaderboard/reports/hm-791844f7ebdacba890a4.md", "plan": "/leaderboard/plans/hm-791844f7ebdacba890a4.md" }, { "id": "hm-794814cee9b674bd8896", "model_label": "anthropic/claude-haiku-4-5-20251001", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-794814cee9b674bd8896.json", "report": "/leaderboard/reports/hm-794814cee9b674bd8896.md", "plan": "/leaderboard/plans/hm-794814cee9b674bd8896.md" }, { "id": "hm-79ab52cd6e1a4a7dfdea", "model_label": "GPT-5 Standard", "lab": "OpenAI", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-79ab52cd6e1a4a7dfdea.json", "report": "/leaderboard/reports/hm-79ab52cd6e1a4a7dfdea.md", "plan": "/leaderboard/plans/hm-79ab52cd6e1a4a7dfdea.md" }, { "id": "hm-7a26a781af96f0b96d73", "model_label": "xai-org/grok-3", "lab": "xAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7a26a781af96f0b96d73.json", "report": "/leaderboard/reports/hm-7a26a781af96f0b96d73.md", "plan": "/leaderboard/plans/hm-7a26a781af96f0b96d73.md" }, { "id": "hm-7b2e1d01c25ff6d8bfbf", "model_label": "Deepseek R1", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7b2e1d01c25ff6d8bfbf.json", "report": "/leaderboard/reports/hm-7b2e1d01c25ff6d8bfbf.md", "plan": "/leaderboard/plans/hm-7b2e1d01c25ff6d8bfbf.md" }, { "id": "hm-7bde46fd1dbbdc20e788", "model_label": "gpt-5-mini-2025-08-07_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7bde46fd1dbbdc20e788.json", "report": "/leaderboard/reports/hm-7bde46fd1dbbdc20e788.md", "plan": "/leaderboard/plans/hm-7bde46fd1dbbdc20e788.md" }, { "id": "hm-7cafad79f2725da09e0b", "model_label": "x-ai/grok-4.7", "lab": "xAI", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7cafad79f2725da09e0b.json", "report": "/leaderboard/reports/hm-7cafad79f2725da09e0b.md", "plan": "/leaderboard/plans/hm-7cafad79f2725da09e0b.md" }, { "id": "hm-7dbdadd9e91b666e921a", "model_label": "Llama-3 Instruct (70B)", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7dbdadd9e91b666e921a.json", "report": "/leaderboard/reports/hm-7dbdadd9e91b666e921a.md", "plan": "/leaderboard/plans/hm-7dbdadd9e91b666e921a.md" }, { "id": "hm-7e1742315ef89becae86", "model_label": "google/gemini-2.5-flash", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7e1742315ef89becae86.json", "report": "/leaderboard/reports/hm-7e1742315ef89becae86.md", "plan": "/leaderboard/plans/hm-7e1742315ef89becae86.md" }, { "id": "hm-7eb3c9e43930484a016b", "model_label": "GPT-5", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7eb3c9e43930484a016b.json", "report": "/leaderboard/reports/hm-7eb3c9e43930484a016b.md", "plan": "/leaderboard/plans/hm-7eb3c9e43930484a016b.md" }, { "id": "hm-7f094de9380bdcc9bcd2", "model_label": "anthropic/claude-opus-4-7", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7f094de9380bdcc9bcd2.json", "report": "/leaderboard/reports/hm-7f094de9380bdcc9bcd2.md", "plan": "/leaderboard/plans/hm-7f094de9380bdcc9bcd2.md" }, { "id": "hm-7f098cdbc8648eac096c", "model_label": "GPT-5 Mini", "lab": "OpenAI", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7f098cdbc8648eac096c.json", "report": "/leaderboard/reports/hm-7f098cdbc8648eac096c.md", "plan": "/leaderboard/plans/hm-7f098cdbc8648eac096c.md" }, { "id": "hm-7f2faa8cec2cd5c021d8", "model_label": "Kimi k2 Thinking", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7f2faa8cec2cd5c021d8.json", "report": "/leaderboard/reports/hm-7f2faa8cec2cd5c021d8.md", "plan": "/leaderboard/plans/hm-7f2faa8cec2cd5c021d8.md" }, { "id": "hm-7f3c5d974dd1fff814a6", "model_label": "openai/o4-mini-low-2025-04-16", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7f3c5d974dd1fff814a6.json", "report": "/leaderboard/reports/hm-7f3c5d974dd1fff814a6.md", "plan": "/leaderboard/plans/hm-7f3c5d974dd1fff814a6.md" }, { "id": "hm-7fbe93aa5ff4ec5733d0", "model_label": "CohereLabs/command-a-03-2025", "lab": "Cohere", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7fbe93aa5ff4ec5733d0.json", "report": "/leaderboard/reports/hm-7fbe93aa5ff4ec5733d0.md", "plan": "/leaderboard/plans/hm-7fbe93aa5ff4ec5733d0.md" }, { "id": "hm-7fd4c47bb798cf25a018", "model_label": "openai/gpt-5-high-2025-08-07", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-7fd4c47bb798cf25a018.json", "report": "/leaderboard/reports/hm-7fd4c47bb798cf25a018.md", "plan": "/leaderboard/plans/hm-7fd4c47bb798cf25a018.md" }, { "id": "hm-8091403352f45f17ffa3", "model_label": "Claude Haiku 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8091403352f45f17ffa3.json", "report": "/leaderboard/reports/hm-8091403352f45f17ffa3.md", "plan": "/leaderboard/plans/hm-8091403352f45f17ffa3.md" }, { "id": "hm-80b202f4818b0d230650", "model_label": "qwen15-7b-chat", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-80b202f4818b0d230650.json", "report": "/leaderboard/reports/hm-80b202f4818b0d230650.md", "plan": "/leaderboard/plans/hm-80b202f4818b0d230650.md" }, { "id": "hm-824985fa80471008ae7f", "model_label": "openai/gpt-6-astra", "lab": "OpenAI", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-824985fa80471008ae7f.json", "report": "/leaderboard/reports/hm-824985fa80471008ae7f.md", "plan": "/leaderboard/plans/hm-824985fa80471008ae7f.md" }, { "id": "hm-82a49faf29a5494bb6eb", "model_label": "claude-sonnet-4-6_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-82a49faf29a5494bb6eb.json", "report": "/leaderboard/reports/hm-82a49faf29a5494bb6eb.md", "plan": "/leaderboard/plans/hm-82a49faf29a5494bb6eb.md" }, { "id": "hm-84a67bfab2c984235f86", "model_label": "Command R", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-84a67bfab2c984235f86.json", "report": "/leaderboard/reports/hm-84a67bfab2c984235f86.md", "plan": "/leaderboard/plans/hm-84a67bfab2c984235f86.md" }, { "id": "hm-84faf198fca96ae24ce5", "model_label": "Mistral-Nemo-Instruct-2407", "lab": "Mistral AI", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-84faf198fca96ae24ce5.json", "report": "/leaderboard/reports/hm-84faf198fca96ae24ce5.md", "plan": "/leaderboard/plans/hm-84faf198fca96ae24ce5.md" }, { "id": "hm-850a6177ec4c9f098b4b", "model_label": "Kimi k2 Thinking", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-850a6177ec4c9f098b4b.json", "report": "/leaderboard/reports/hm-850a6177ec4c9f098b4b.md", "plan": "/leaderboard/plans/hm-850a6177ec4c9f098b4b.md" }, { "id": "hm-85adf6253bf8b3eb56fb", "model_label": "o4-mini-high", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-85adf6253bf8b3eb56fb.json", "report": "/leaderboard/reports/hm-85adf6253bf8b3eb56fb.md", "plan": "/leaderboard/plans/hm-85adf6253bf8b3eb56fb.md" }, { "id": "hm-85e49abdf1e2e436a150", "model_label": "Phi-3-mini-128k-instruct", "lab": "Microsoft", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-85e49abdf1e2e436a150.json", "report": "/leaderboard/reports/hm-85e49abdf1e2e436a150.md", "plan": "/leaderboard/plans/hm-85e49abdf1e2e436a150.md" }, { "id": "hm-86fcb13415917f3a1b6c", "model_label": "Llama 3.1 405B", "lab": "Meta", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-86fcb13415917f3a1b6c.json", "report": "/leaderboard/reports/hm-86fcb13415917f3a1b6c.md", "plan": "/leaderboard/plans/hm-86fcb13415917f3a1b6c.md" }, { "id": "hm-871b9dcc211ba3303bf2", "model_label": "microsoft/Phi-4-mini-instruct", "lab": "Microsoft", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-871b9dcc211ba3303bf2.json", "report": "/leaderboard/reports/hm-871b9dcc211ba3303bf2.md", "plan": "/leaderboard/plans/hm-871b9dcc211ba3303bf2.md" }, { "id": "hm-8774cad3959b8be6c432", "model_label": "Kimi k2", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8774cad3959b8be6c432.json", "report": "/leaderboard/reports/hm-8774cad3959b8be6c432.md", "plan": "/leaderboard/plans/hm-8774cad3959b8be6c432.md" }, { "id": "hm-88091268baf1211e563e", "model_label": "llama-32-3b-instruct", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-88091268baf1211e563e.json", "report": "/leaderboard/reports/hm-88091268baf1211e563e.md", "plan": "/leaderboard/plans/hm-88091268baf1211e563e.md" }, { "id": "hm-8861c260e02949b71a86", "model_label": "llama-2-7b-chat", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8861c260e02949b71a86.json", "report": "/leaderboard/reports/hm-8861c260e02949b71a86.md", "plan": "/leaderboard/plans/hm-8861c260e02949b71a86.md" }, { "id": "hm-88ae90da7063e04932ff", "model_label": "Claude Sonnet 4.6", "lab": "Anthropic", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-88ae90da7063e04932ff.json", "report": "/leaderboard/reports/hm-88ae90da7063e04932ff.md", "plan": "/leaderboard/plans/hm-88ae90da7063e04932ff.md" }, { "id": "hm-89019655682f670b38ee", "model_label": "Command R+", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-89019655682f670b38ee.json", "report": "/leaderboard/reports/hm-89019655682f670b38ee.md", "plan": "/leaderboard/plans/hm-89019655682f670b38ee.md" }, { "id": "hm-8938349b6226b64def55", "model_label": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "lab": "Meta", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8938349b6226b64def55.json", "report": "/leaderboard/reports/hm-8938349b6226b64def55.md", "plan": "/leaderboard/plans/hm-8938349b6226b64def55.md" }, { "id": "hm-8939051f031726386725", "model_label": "Gemini 2.5 Flash (Sep)", "lab": "Google", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8939051f031726386725.json", "report": "/leaderboard/reports/hm-8939051f031726386725.md", "plan": "/leaderboard/plans/hm-8939051f031726386725.md" }, { "id": "hm-89750f1e924d7a710094", "model_label": "qwen/qwen3-8b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-89750f1e924d7a710094.json", "report": "/leaderboard/reports/hm-89750f1e924d7a710094.md", "plan": "/leaderboard/plans/hm-89750f1e924d7a710094.md" }, { "id": "hm-8b38255834f89d51efd7", "model_label": "llama2-chat-13b", "lab": "Meta", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8b38255834f89d51efd7.json", "report": "/leaderboard/reports/hm-8b38255834f89d51efd7.md", "plan": "/leaderboard/plans/hm-8b38255834f89d51efd7.md" }, { "id": "hm-8b4b782fd2ff64b36845", "model_label": "openai/o4-mini-high-2025-04-16", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8b4b782fd2ff64b36845.json", "report": "/leaderboard/reports/hm-8b4b782fd2ff64b36845.md", "plan": "/leaderboard/plans/hm-8b4b782fd2ff64b36845.md" }, { "id": "hm-8c19579f1293316c1f71", "model_label": "kimi-k3_max", "lab": "Moonshot", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8c19579f1293316c1f71.json", "report": "/leaderboard/reports/hm-8c19579f1293316c1f71.md", "plan": "/leaderboard/plans/hm-8c19579f1293316c1f71.md" }, { "id": "hm-8c746272e45e9d690a89", "model_label": "amazon/nova-micro-v1:0", "lab": "Amazon", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8c746272e45e9d690a89.json", "report": "/leaderboard/reports/hm-8c746272e45e9d690a89.md", "plan": "/leaderboard/plans/hm-8c746272e45e9d690a89.md" }, { "id": "hm-8ce2c30d3fabfde04889", "model_label": "GPT-5", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8ce2c30d3fabfde04889.json", "report": "/leaderboard/reports/hm-8ce2c30d3fabfde04889.md", "plan": "/leaderboard/plans/hm-8ce2c30d3fabfde04889.md" }, { "id": "hm-8d026ca79ac2ac533df1", "model_label": "nvidia/Nemotron-3-Nano-30B-A3B", "lab": "NVIDIA", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8d026ca79ac2ac533df1.json", "report": "/leaderboard/reports/hm-8d026ca79ac2ac533df1.md", "plan": "/leaderboard/plans/hm-8d026ca79ac2ac533df1.md" }, { "id": "hm-8d303cb07d092b94027e", "model_label": "openai/gpt-5.2-high-2025-12-11", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8d303cb07d092b94027e.json", "report": "/leaderboard/reports/hm-8d303cb07d092b94027e.md", "plan": "/leaderboard/plans/hm-8d303cb07d092b94027e.md" }, { "id": "hm-8d4600e5017b30cc2eb4", "model_label": "inkling-small_xhigh", "lab": "Thinking Machines", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8d4600e5017b30cc2eb4.json", "report": "/leaderboard/reports/hm-8d4600e5017b30cc2eb4.md", "plan": "/leaderboard/plans/hm-8d4600e5017b30cc2eb4.md" }, { "id": "hm-8d5b45ce5e359fc8cfc7", "model_label": "openai/gpt-5-mini-2025-08-07", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8d5b45ce5e359fc8cfc7.json", "report": "/leaderboard/reports/hm-8d5b45ce5e359fc8cfc7.md", "plan": "/leaderboard/plans/hm-8d5b45ce5e359fc8cfc7.md" }, { "id": "hm-8e9f448affeb1d85c877", "model_label": "gpt-4o-2024-08-06", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8e9f448affeb1d85c877.json", "report": "/leaderboard/reports/hm-8e9f448affeb1d85c877.md", "plan": "/leaderboard/plans/hm-8e9f448affeb1d85c877.md" }, { "id": "hm-8ea45f1609b80485dadc", "model_label": "ai21labs/jamba-mini-1.7-2025-07", "lab": "AI21 Labs", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8ea45f1609b80485dadc.json", "report": "/leaderboard/reports/hm-8ea45f1609b80485dadc.md", "plan": "/leaderboard/plans/hm-8ea45f1609b80485dadc.md" }, { "id": "hm-8eab2668269866cf5cc2", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8eab2668269866cf5cc2.json", "report": "/leaderboard/reports/hm-8eab2668269866cf5cc2.md", "plan": "/leaderboard/plans/hm-8eab2668269866cf5cc2.md" }, { "id": "hm-8ec7cfdf3656dcaed141", "model_label": "Llama 3.1 70B Tulu 3 SFT", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8ec7cfdf3656dcaed141.json", "report": "/leaderboard/reports/hm-8ec7cfdf3656dcaed141.md", "plan": "/leaderboard/plans/hm-8ec7cfdf3656dcaed141.md" }, { "id": "hm-8f50b1638f8a3c3ecfd6", "model_label": "gemini-3.7-flash_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8f50b1638f8a3c3ecfd6.json", "report": "/leaderboard/reports/hm-8f50b1638f8a3c3ecfd6.md", "plan": "/leaderboard/plans/hm-8f50b1638f8a3c3ecfd6.md" }, { "id": "hm-8ff77c46e6fcc570ec23", "model_label": "ChatGPT", "lab": "OpenAI", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-8ff77c46e6fcc570ec23.json", "report": "/leaderboard/reports/hm-8ff77c46e6fcc570ec23.md", "plan": "/leaderboard/plans/hm-8ff77c46e6fcc570ec23.md" }, { "id": "hm-908fac5f94678a87e60d", "model_label": "google/gemma-3-12b-it", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-908fac5f94678a87e60d.json", "report": "/leaderboard/reports/hm-908fac5f94678a87e60d.md", "plan": "/leaderboard/plans/hm-908fac5f94678a87e60d.md" }, { "id": "hm-90ca76aff0b2a2662dad", "model_label": "Command R+", "lab": "Cohere", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-90ca76aff0b2a2662dad.json", "report": "/leaderboard/reports/hm-90ca76aff0b2a2662dad.md", "plan": "/leaderboard/plans/hm-90ca76aff0b2a2662dad.md" }, { "id": "hm-910004ba0e2777ece6fa", "model_label": "openai/gpt-5.4-nano-2026-03-17", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-910004ba0e2777ece6fa.json", "report": "/leaderboard/reports/hm-910004ba0e2777ece6fa.md", "plan": "/leaderboard/plans/hm-910004ba0e2777ece6fa.md" }, { "id": "hm-9119faddf871008869f9", "model_label": "Gemini 3.1 Pro", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9119faddf871008869f9.json", "report": "/leaderboard/reports/hm-9119faddf871008869f9.md", "plan": "/leaderboard/plans/hm-9119faddf871008869f9.md" }, { "id": "hm-91ced5e79c4b60d3261c", "model_label": "GPT-OSS-120B", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-91ced5e79c4b60d3261c.json", "report": "/leaderboard/reports/hm-91ced5e79c4b60d3261c.md", "plan": "/leaderboard/plans/hm-91ced5e79c4b60d3261c.md" }, { "id": "hm-91e232569b428b50bf15", "model_label": "Llama-3.1-8B-Instruct", "lab": "Meta", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-91e232569b428b50bf15.json", "report": "/leaderboard/reports/hm-91e232569b428b50bf15.md", "plan": "/leaderboard/plans/hm-91e232569b428b50bf15.md" }, { "id": "hm-92331d2e1960ec77d7be", "model_label": "Gemini 2.0 Flash Experimental", "lab": "Google", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-92331d2e1960ec77d7be.json", "report": "/leaderboard/reports/hm-92331d2e1960ec77d7be.md", "plan": "/leaderboard/plans/hm-92331d2e1960ec77d7be.md" }, { "id": "hm-92677bc667011d9bb997", "model_label": "ai21labs/jamba-large-1.7-2025-07", "lab": "AI21 Labs", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-92677bc667011d9bb997.json", "report": "/leaderboard/reports/hm-92677bc667011d9bb997.md", "plan": "/leaderboard/plans/hm-92677bc667011d9bb997.md" }, { "id": "hm-9349156857e3545bfb41", "model_label": "GPT-5 (minimal)", "lab": "OpenAI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9349156857e3545bfb41.json", "report": "/leaderboard/reports/hm-9349156857e3545bfb41.md", "plan": "/leaderboard/plans/hm-9349156857e3545bfb41.md" }, { "id": "hm-940231dc96f780b58028", "model_label": "qwen25-14b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-940231dc96f780b58028.json", "report": "/leaderboard/reports/hm-940231dc96f780b58028.md", "plan": "/leaderboard/plans/hm-940231dc96f780b58028.md" }, { "id": "hm-948fda3d164cdddaf7de", "model_label": "Deepseek V3", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-948fda3d164cdddaf7de.json", "report": "/leaderboard/reports/hm-948fda3d164cdddaf7de.md", "plan": "/leaderboard/plans/hm-948fda3d164cdddaf7de.md" }, { "id": "hm-9517a512c76a283ee243", "model_label": "o1-mini", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9517a512c76a283ee243.json", "report": "/leaderboard/reports/hm-9517a512c76a283ee243.md", "plan": "/leaderboard/plans/hm-9517a512c76a283ee243.md" }, { "id": "hm-951b75ca25edb2d94c55", "model_label": "GPT-5.2 (medium)", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-951b75ca25edb2d94c55.json", "report": "/leaderboard/reports/hm-951b75ca25edb2d94c55.md", "plan": "/leaderboard/plans/hm-951b75ca25edb2d94c55.md" }, { "id": "hm-95ac1bc2ceb6938935ec", "model_label": "google/gemma-4-31b-it", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-95ac1bc2ceb6938935ec.json", "report": "/leaderboard/reports/hm-95ac1bc2ceb6938935ec.md", "plan": "/leaderboard/plans/hm-95ac1bc2ceb6938935ec.md" }, { "id": "hm-970e5a9028f008a2a50e", "model_label": "Llama 3.1 8B Tulu 3 PPO RLVF", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-970e5a9028f008a2a50e.json", "report": "/leaderboard/reports/hm-970e5a9028f008a2a50e.md", "plan": "/leaderboard/plans/hm-970e5a9028f008a2a50e.md" }, { "id": "hm-972516e65c0d04953fe5", "model_label": "GPT-5.5", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-972516e65c0d04953fe5.json", "report": "/leaderboard/reports/hm-972516e65c0d04953fe5.md", "plan": "/leaderboard/plans/hm-972516e65c0d04953fe5.md" }, { "id": "hm-9737133159c58fb7313f", "model_label": "llama-31-70b-instruct", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9737133159c58fb7313f.json", "report": "/leaderboard/reports/hm-9737133159c58fb7313f.md", "plan": "/leaderboard/plans/hm-9737133159c58fb7313f.md" }, { "id": "hm-976caac9a76a2a2a2ae4", "model_label": "Deepseek V3", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-976caac9a76a2a2a2ae4.json", "report": "/leaderboard/reports/hm-976caac9a76a2a2a2ae4.md", "plan": "/leaderboard/plans/hm-976caac9a76a2a2a2ae4.md" }, { "id": "hm-97cd5c3d2fe25578b094", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-97cd5c3d2fe25578b094.json", "report": "/leaderboard/reports/hm-97cd5c3d2fe25578b094.md", "plan": "/leaderboard/plans/hm-97cd5c3d2fe25578b094.md" }, { "id": "hm-9848a84a4c5e5e5f485a", "model_label": "gpt-5.2-2025-12-11_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9848a84a4c5e5e5f485a.json", "report": "/leaderboard/reports/hm-9848a84a4c5e5e5f485a.md", "plan": "/leaderboard/plans/hm-9848a84a4c5e5e5f485a.md" }, { "id": "hm-98c0cda618b4e145a375", "model_label": "Llama 3.1 70B Tulu 3 PPO RLVF", "lab": "Allen Institute for AI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-98c0cda618b4e145a375.json", "report": "/leaderboard/reports/hm-98c0cda618b4e145a375.md", "plan": "/leaderboard/plans/hm-98c0cda618b4e145a375.md" }, { "id": "hm-98caea8b8569ccf3f92f", "model_label": "GPT-4o", "lab": "OpenAI", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-98caea8b8569ccf3f92f.json", "report": "/leaderboard/reports/hm-98caea8b8569ccf3f92f.md", "plan": "/leaderboard/plans/hm-98caea8b8569ccf3f92f.md" }, { "id": "hm-9909c5df0b4a1507d76f", "model_label": "deepseek-ai/DeepSeek-V3.2", "lab": "DeepSeek", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9909c5df0b4a1507d76f.json", "report": "/leaderboard/reports/hm-9909c5df0b4a1507d76f.md", "plan": "/leaderboard/plans/hm-9909c5df0b4a1507d76f.md" }, { "id": "hm-9aa1228162ae07f9d860", "model_label": "GPT-5.2", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9aa1228162ae07f9d860.json", "report": "/leaderboard/reports/hm-9aa1228162ae07f9d860.md", "plan": "/leaderboard/plans/hm-9aa1228162ae07f9d860.md" }, { "id": "hm-9b1def4b1261444869f0", "model_label": "Gemini 3.1 Flash-Lite", "lab": "Google", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9b1def4b1261444869f0.json", "report": "/leaderboard/reports/hm-9b1def4b1261444869f0.md", "plan": "/leaderboard/plans/hm-9b1def4b1261444869f0.md" }, { "id": "hm-9bfc5c1e4110fab5de29", "model_label": "openai/o3-pro", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9bfc5c1e4110fab5de29.json", "report": "/leaderboard/reports/hm-9bfc5c1e4110fab5de29.md", "plan": "/leaderboard/plans/hm-9bfc5c1e4110fab5de29.md" }, { "id": "hm-9d23eea79702a7e1e071", "model_label": "Claude Haiku 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9d23eea79702a7e1e071.json", "report": "/leaderboard/reports/hm-9d23eea79702a7e1e071.md", "plan": "/leaderboard/plans/hm-9d23eea79702a7e1e071.md" }, { "id": "hm-9e154c8687499fc8c56f", "model_label": "inceptionlabs/mercury-2", "lab": "Inception", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9e154c8687499fc8c56f.json", "report": "/leaderboard/reports/hm-9e154c8687499fc8c56f.md", "plan": "/leaderboard/plans/hm-9e154c8687499fc8c56f.md" }, { "id": "hm-9ec5f1b4bf161c378d89", "model_label": "deepseek-ai/DeepSeek-V3", "lab": "DeepSeek", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9ec5f1b4bf161c378d89.json", "report": "/leaderboard/reports/hm-9ec5f1b4bf161c378d89.md", "plan": "/leaderboard/plans/hm-9ec5f1b4bf161c378d89.md" }, { "id": "hm-9f2601f5b434fb9bc20e", "model_label": "Claude Opus 4.1", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9f2601f5b434fb9bc20e.json", "report": "/leaderboard/reports/hm-9f2601f5b434fb9bc20e.md", "plan": "/leaderboard/plans/hm-9f2601f5b434fb9bc20e.md" }, { "id": "hm-9f8027b511e52ea99e2d", "model_label": "o4-mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-9f8027b511e52ea99e2d.json", "report": "/leaderboard/reports/hm-9f8027b511e52ea99e2d.md", "plan": "/leaderboard/plans/hm-9f8027b511e52ea99e2d.md" }, { "id": "hm-a022b583ccb03c7b0684", "model_label": "claude-opus-5-5_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a022b583ccb03c7b0684.json", "report": "/leaderboard/reports/hm-a022b583ccb03c7b0684.md", "plan": "/leaderboard/plans/hm-a022b583ccb03c7b0684.md" }, { "id": "hm-a289727ed9db12978f47", "model_label": "deepseek-v4-pro_max", "lab": "DeepSeek", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a289727ed9db12978f47.json", "report": "/leaderboard/reports/hm-a289727ed9db12978f47.md", "plan": "/leaderboard/plans/hm-a289727ed9db12978f47.md" }, { "id": "hm-a45b6069dec1dc2fb589", "model_label": "Gemini 3.5 Flash", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a45b6069dec1dc2fb589.json", "report": "/leaderboard/reports/hm-a45b6069dec1dc2fb589.md", "plan": "/leaderboard/plans/hm-a45b6069dec1dc2fb589.md" }, { "id": "hm-a4970a9441020a71db5f", "model_label": "deepseek-r1", "lab": "DeepSeek", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a4970a9441020a71db5f.json", "report": "/leaderboard/reports/hm-a4970a9441020a71db5f.md", "plan": "/leaderboard/plans/hm-a4970a9441020a71db5f.md" }, { "id": "hm-a5d2b634c4238123a42a", "model_label": "gpt-5.4-pro-2026-03-05_xhigh", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a5d2b634c4238123a42a.json", "report": "/leaderboard/reports/hm-a5d2b634c4238123a42a.md", "plan": "/leaderboard/plans/hm-a5d2b634c4238123a42a.md" }, { "id": "hm-a7a0ea6dfed7656f496b", "model_label": "Kimi k2", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a7a0ea6dfed7656f496b.json", "report": "/leaderboard/reports/hm-a7a0ea6dfed7656f496b.md", "plan": "/leaderboard/plans/hm-a7a0ea6dfed7656f496b.md" }, { "id": "hm-a82487bbba434298a0bd", "model_label": "qwen/qwen3-32b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a82487bbba434298a0bd.json", "report": "/leaderboard/reports/hm-a82487bbba434298a0bd.md", "plan": "/leaderboard/plans/hm-a82487bbba434298a0bd.md" }, { "id": "hm-a8c141ab09a8d7483628", "model_label": "Claude 3 Haiku", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a8c141ab09a8d7483628.json", "report": "/leaderboard/reports/hm-a8c141ab09a8d7483628.md", "plan": "/leaderboard/plans/hm-a8c141ab09a8d7483628.md" }, { "id": "hm-a8d192f55fa63e58a479", "model_label": "openai/gpt-5.4-pro-2026-03-05", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a8d192f55fa63e58a479.json", "report": "/leaderboard/reports/hm-a8d192f55fa63e58a479.md", "plan": "/leaderboard/plans/hm-a8d192f55fa63e58a479.md" }, { "id": "hm-a965d2bb39d377283b90", "model_label": "deepseek-v4-flash-0731_max", "lab": "DeepSeek", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a965d2bb39d377283b90.json", "report": "/leaderboard/reports/hm-a965d2bb39d377283b90.md", "plan": "/leaderboard/plans/hm-a965d2bb39d377283b90.md" }, { "id": "hm-a97445c80822f2ba5e33", "model_label": "Llama-3 Instruct (70B)", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-a97445c80822f2ba5e33.json", "report": "/leaderboard/reports/hm-a97445c80822f2ba5e33.md", "plan": "/leaderboard/plans/hm-a97445c80822f2ba5e33.md" }, { "id": "hm-ab525d59eeab574d3c9b", "model_label": "Claude 3 Haiku", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ab525d59eeab574d3c9b.json", "report": "/leaderboard/reports/hm-ab525d59eeab574d3c9b.md", "plan": "/leaderboard/plans/hm-ab525d59eeab574d3c9b.md" }, { "id": "hm-ad9d02b2bf1d275b01f4", "model_label": "xai-org/grok-4-1-fast-non-reasoning", "lab": "xAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ad9d02b2bf1d275b01f4.json", "report": "/leaderboard/reports/hm-ad9d02b2bf1d275b01f4.md", "plan": "/leaderboard/plans/hm-ad9d02b2bf1d275b01f4.md" }, { "id": "hm-ada123459c4984f7fd3e", "model_label": "gemini-3.6-flash_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ada123459c4984f7fd3e.json", "report": "/leaderboard/reports/hm-ada123459c4984f7fd3e.md", "plan": "/leaderboard/plans/hm-ada123459c4984f7fd3e.md" }, { "id": "hm-ae3e1d0ba11fbec3e775", "model_label": "Deepseek V3", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ae3e1d0ba11fbec3e775.json", "report": "/leaderboard/reports/hm-ae3e1d0ba11fbec3e775.md", "plan": "/leaderboard/plans/hm-ae3e1d0ba11fbec3e775.md" }, { "id": "hm-aeb422f24a68be25bd1c", "model_label": "mistralai/mistral-medium-2508", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-aeb422f24a68be25bd1c.json", "report": "/leaderboard/reports/hm-aeb422f24a68be25bd1c.md", "plan": "/leaderboard/plans/hm-aeb422f24a68be25bd1c.md" }, { "id": "hm-af12abed554daab7447e", "model_label": "Llama 3.1 8B Instruct", "lab": "Meta", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-af12abed554daab7447e.json", "report": "/leaderboard/reports/hm-af12abed554daab7447e.md", "plan": "/leaderboard/plans/hm-af12abed554daab7447e.md" }, { "id": "hm-af5ee94e8de8a8a8b45c", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-af5ee94e8de8a8a8b45c.json", "report": "/leaderboard/reports/hm-af5ee94e8de8a8a8b45c.md", "plan": "/leaderboard/plans/hm-af5ee94e8de8a8a8b45c.md" }, { "id": "hm-afaaa43b65554c998ab8", "model_label": "gpt-4o", "lab": "OpenAI", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-afaaa43b65554c998ab8.json", "report": "/leaderboard/reports/hm-afaaa43b65554c998ab8.md", "plan": "/leaderboard/plans/hm-afaaa43b65554c998ab8.md" }, { "id": "hm-aff297eca77d064f9343", "model_label": "UnifiedQA 3B", "lab": "Allen Institute for AI", "source": "truthfulqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-aff297eca77d064f9343.json", "report": "/leaderboard/reports/hm-aff297eca77d064f9343.md", "plan": "/leaderboard/plans/hm-aff297eca77d064f9343.md" }, { "id": "hm-b07dd4ab7b9d03048c7e", "model_label": "Llama 3.1 70B Instruct", "lab": "Meta", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b07dd4ab7b9d03048c7e.json", "report": "/leaderboard/reports/hm-b07dd4ab7b9d03048c7e.md", "plan": "/leaderboard/plans/hm-b07dd4ab7b9d03048c7e.md" }, { "id": "hm-b0b7b1b68499ffadc794", "model_label": "openai/gpt-5.6-sol", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b0b7b1b68499ffadc794.json", "report": "/leaderboard/reports/hm-b0b7b1b68499ffadc794.md", "plan": "/leaderboard/plans/hm-b0b7b1b68499ffadc794.md" }, { "id": "hm-b0cc80bb712ecc9ab680", "model_label": "kimi-k2.5", "lab": "Moonshot", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b0cc80bb712ecc9ab680.json", "report": "/leaderboard/reports/hm-b0cc80bb712ecc9ab680.md", "plan": "/leaderboard/plans/hm-b0cc80bb712ecc9ab680.md" }, { "id": "hm-b11f9dc0e3afeb489837", "model_label": "claude-opus-4-6_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b11f9dc0e3afeb489837.json", "report": "/leaderboard/reports/hm-b11f9dc0e3afeb489837.md", "plan": "/leaderboard/plans/hm-b11f9dc0e3afeb489837.md" }, { "id": "hm-b120331931bffe12f355", "model_label": "openai/gpt-6-astra", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b120331931bffe12f355.json", "report": "/leaderboard/reports/hm-b120331931bffe12f355.md", "plan": "/leaderboard/plans/hm-b120331931bffe12f355.md" }, { "id": "hm-b15283d3719165ad8563", "model_label": "Claude Haiku 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b15283d3719165ad8563.json", "report": "/leaderboard/reports/hm-b15283d3719165ad8563.md", "plan": "/leaderboard/plans/hm-b15283d3719165ad8563.md" }, { "id": "hm-b18efcc24868c696c0f8", "model_label": "CohereLabs/command-r-plus-08-2024", "lab": "Cohere", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b18efcc24868c696c0f8.json", "report": "/leaderboard/reports/hm-b18efcc24868c696c0f8.md", "plan": "/leaderboard/plans/hm-b18efcc24868c696c0f8.md" }, { "id": "hm-b200cb1c3b022f7740f7", "model_label": "anthropic/claude-sonnet-4-5-20250929", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b200cb1c3b022f7740f7.json", "report": "/leaderboard/reports/hm-b200cb1c3b022f7740f7.md", "plan": "/leaderboard/plans/hm-b200cb1c3b022f7740f7.md" }, { "id": "hm-b2bdaecbd711d61b9e12", "model_label": "Gemini 3 Pro Preview", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b2bdaecbd711d61b9e12.json", "report": "/leaderboard/reports/hm-b2bdaecbd711d61b9e12.md", "plan": "/leaderboard/plans/hm-b2bdaecbd711d61b9e12.md" }, { "id": "hm-b34388297a056cd42a18", "model_label": "Grok 4", "lab": "xAI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b34388297a056cd42a18.json", "report": "/leaderboard/reports/hm-b34388297a056cd42a18.md", "plan": "/leaderboard/plans/hm-b34388297a056cd42a18.md" }, { "id": "hm-b441f7f1b1095f82b87f", "model_label": "MiniMaxAI/minimax-m2p7", "lab": "MiniMax", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b441f7f1b1095f82b87f.json", "report": "/leaderboard/reports/hm-b441f7f1b1095f82b87f.md", "plan": "/leaderboard/plans/hm-b441f7f1b1095f82b87f.md" }, { "id": "hm-b49bf5ba0220f70af21d", "model_label": "GPT-3.5 Turbo", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b49bf5ba0220f70af21d.json", "report": "/leaderboard/reports/hm-b49bf5ba0220f70af21d.md", "plan": "/leaderboard/plans/hm-b49bf5ba0220f70af21d.md" }, { "id": "hm-b5f5a736e02022bea393", "model_label": "gpt-4o-mini-2024-07-18", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b5f5a736e02022bea393.json", "report": "/leaderboard/reports/hm-b5f5a736e02022bea393.md", "plan": "/leaderboard/plans/hm-b5f5a736e02022bea393.md" }, { "id": "hm-b62798ec47da4e8dbe80", "model_label": "GPT-5 mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b62798ec47da4e8dbe80.json", "report": "/leaderboard/reports/hm-b62798ec47da4e8dbe80.md", "plan": "/leaderboard/plans/hm-b62798ec47da4e8dbe80.md" }, { "id": "hm-b6788f1b6f336e3f3880", "model_label": "ai21labs/jamba-mini-2", "lab": "AI21 Labs", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b6788f1b6f336e3f3880.json", "report": "/leaderboard/reports/hm-b6788f1b6f336e3f3880.md", "plan": "/leaderboard/plans/hm-b6788f1b6f336e3f3880.md" }, { "id": "hm-b7023dfad0f2c2e8d2fa", "model_label": "Grok-4", "lab": "xAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b7023dfad0f2c2e8d2fa.json", "report": "/leaderboard/reports/hm-b7023dfad0f2c2e8d2fa.md", "plan": "/leaderboard/plans/hm-b7023dfad0f2c2e8d2fa.md" }, { "id": "hm-b712ba4861e6310c4974", "model_label": "Command R", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b712ba4861e6310c4974.json", "report": "/leaderboard/reports/hm-b712ba4861e6310c4974.md", "plan": "/leaderboard/plans/hm-b712ba4861e6310c4974.md" }, { "id": "hm-b9843cc5e30c99c7093d", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b9843cc5e30c99c7093d.json", "report": "/leaderboard/reports/hm-b9843cc5e30c99c7093d.md", "plan": "/leaderboard/plans/hm-b9843cc5e30c99c7093d.md" }, { "id": "hm-b9b9f78caa681df69e38", "model_label": "Llama 3.1 70B Base", "lab": "Meta", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b9b9f78caa681df69e38.json", "report": "/leaderboard/reports/hm-b9b9f78caa681df69e38.md", "plan": "/leaderboard/plans/hm-b9b9f78caa681df69e38.md" }, { "id": "hm-b9d35b541be84516ebb2", "model_label": "gpt-5.6-sol_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b9d35b541be84516ebb2.json", "report": "/leaderboard/reports/hm-b9d35b541be84516ebb2.md", "plan": "/leaderboard/plans/hm-b9d35b541be84516ebb2.md" }, { "id": "hm-b9f42f9ba6b1e7dbe663", "model_label": "GPT-4 Turbo", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-b9f42f9ba6b1e7dbe663.json", "report": "/leaderboard/reports/hm-b9f42f9ba6b1e7dbe663.md", "plan": "/leaderboard/plans/hm-b9f42f9ba6b1e7dbe663.md" }, { "id": "hm-ba98b75f3f1194d98945", "model_label": "o3-high", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ba98b75f3f1194d98945.json", "report": "/leaderboard/reports/hm-ba98b75f3f1194d98945.md", "plan": "/leaderboard/plans/hm-ba98b75f3f1194d98945.md" }, { "id": "hm-baa77ab27a99a25c59c9", "model_label": "GPT-4o mini", "lab": "OpenAI", "source": "facts", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-baa77ab27a99a25c59c9.json", "report": "/leaderboard/reports/hm-baa77ab27a99a25c59c9.md", "plan": "/leaderboard/plans/hm-baa77ab27a99a25c59c9.md" }, { "id": "hm-bae7b1c4bddfa6e09b3c", "model_label": "openai/gpt-5.4-mini-2026-03-17", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bae7b1c4bddfa6e09b3c.json", "report": "/leaderboard/reports/hm-bae7b1c4bddfa6e09b3c.md", "plan": "/leaderboard/plans/hm-bae7b1c4bddfa6e09b3c.md" }, { "id": "hm-bb6497ae2bf0498543a9", "model_label": "Kimi k2", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bb6497ae2bf0498543a9.json", "report": "/leaderboard/reports/hm-bb6497ae2bf0498543a9.md", "plan": "/leaderboard/plans/hm-bb6497ae2bf0498543a9.md" }, { "id": "hm-bbc17f792952227a9cc3", "model_label": "llama-31-8b-instruct", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bbc17f792952227a9cc3.json", "report": "/leaderboard/reports/hm-bbc17f792952227a9cc3.md", "plan": "/leaderboard/plans/hm-bbc17f792952227a9cc3.md" }, { "id": "hm-bc0e28d2991eb234becb", "model_label": "CohereLabs/c4ai-aya-expanse-32b", "lab": "Cohere", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bc0e28d2991eb234becb.json", "report": "/leaderboard/reports/hm-bc0e28d2991eb234becb.md", "plan": "/leaderboard/plans/hm-bc0e28d2991eb234becb.md" }, { "id": "hm-bc2c2523e66281a5c7f5", "model_label": "gpt-5.2-2025-12-11_medium", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bc2c2523e66281a5c7f5.json", "report": "/leaderboard/reports/hm-bc2c2523e66281a5c7f5.md", "plan": "/leaderboard/plans/hm-bc2c2523e66281a5c7f5.md" }, { "id": "hm-bc2c6ae80766c741d87f", "model_label": "Claude 4.5 Haiku", "lab": "Anthropic", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bc2c6ae80766c741d87f.json", "report": "/leaderboard/reports/hm-bc2c6ae80766c741d87f.md", "plan": "/leaderboard/plans/hm-bc2c6ae80766c741d87f.md" }, { "id": "hm-bd7135e3fa7e5df7bf07", "model_label": "claude-sonnet-4-5-20250929_59K", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bd7135e3fa7e5df7bf07.json", "report": "/leaderboard/reports/hm-bd7135e3fa7e5df7bf07.md", "plan": "/leaderboard/plans/hm-bd7135e3fa7e5df7bf07.md" }, { "id": "hm-bda17e252902080bdb40", "model_label": "qwen/qwen3-next-80b-a3b-thinking", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bda17e252902080bdb40.json", "report": "/leaderboard/reports/hm-bda17e252902080bdb40.md", "plan": "/leaderboard/plans/hm-bda17e252902080bdb40.md" }, { "id": "hm-bdf3c84a84600f8baf69", "model_label": "gpt-4o-mini-2024-07-18", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bdf3c84a84600f8baf69.json", "report": "/leaderboard/reports/hm-bdf3c84a84600f8baf69.md", "plan": "/leaderboard/plans/hm-bdf3c84a84600f8baf69.md" }, { "id": "hm-be4e0bc65c00b12b96aa", "model_label": "DeepSeek R1 Distill Llama 70B", "lab": "DeepSeek", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-be4e0bc65c00b12b96aa.json", "report": "/leaderboard/reports/hm-be4e0bc65c00b12b96aa.md", "plan": "/leaderboard/plans/hm-be4e0bc65c00b12b96aa.md" }, { "id": "hm-bebc5345ce3b5e9506e3", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bebc5345ce3b5e9506e3.json", "report": "/leaderboard/reports/hm-bebc5345ce3b5e9506e3.md", "plan": "/leaderboard/plans/hm-bebc5345ce3b5e9506e3.md" }, { "id": "hm-bec08bb4d01baec35bf3", "model_label": "Vicuna-7B", "lab": "LMSYS", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bec08bb4d01baec35bf3.json", "report": "/leaderboard/reports/hm-bec08bb4d01baec35bf3.md", "plan": "/leaderboard/plans/hm-bec08bb4d01baec35bf3.md" }, { "id": "hm-becea53f5f322e6df04f", "model_label": "grok-4.5_high", "lab": "xAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-becea53f5f322e6df04f.json", "report": "/leaderboard/reports/hm-becea53f5f322e6df04f.md", "plan": "/leaderboard/plans/hm-becea53f5f322e6df04f.md" }, { "id": "hm-bfa2305d04775dc9691a", "model_label": "gpt-4o-2024-05-13", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-bfa2305d04775dc9691a.json", "report": "/leaderboard/reports/hm-bfa2305d04775dc9691a.md", "plan": "/leaderboard/plans/hm-bfa2305d04775dc9691a.md" }, { "id": "hm-c00d1282176bdf31058a", "model_label": "gpt-5.4-nano-2026-03-17_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c00d1282176bdf31058a.json", "report": "/leaderboard/reports/hm-c00d1282176bdf31058a.md", "plan": "/leaderboard/plans/hm-c00d1282176bdf31058a.md" }, { "id": "hm-c0363974bef8195dc76e", "model_label": "gpt-4-turbo", "lab": "OpenAI", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c0363974bef8195dc76e.json", "report": "/leaderboard/reports/hm-c0363974bef8195dc76e.md", "plan": "/leaderboard/plans/hm-c0363974bef8195dc76e.md" }, { "id": "hm-c048e2841efe02fcd316", "model_label": "google/gemini-2.5-flash-lite", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c048e2841efe02fcd316.json", "report": "/leaderboard/reports/hm-c048e2841efe02fcd316.md", "plan": "/leaderboard/plans/hm-c048e2841efe02fcd316.md" }, { "id": "hm-c08800c9f2c63864e0bc", "model_label": "gpt-5.2-2025-12-11_low", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c08800c9f2c63864e0bc.json", "report": "/leaderboard/reports/hm-c08800c9f2c63864e0bc.md", "plan": "/leaderboard/plans/hm-c08800c9f2c63864e0bc.md" }, { "id": "hm-c0a8db5681bb1853558e", "model_label": "qwen3.5-flash", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c0a8db5681bb1853558e.json", "report": "/leaderboard/reports/hm-c0a8db5681bb1853558e.md", "plan": "/leaderboard/plans/hm-c0a8db5681bb1853558e.md" }, { "id": "hm-c0b594469a7fb33f6daf", "model_label": "Claude Opus 4.7", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c0b594469a7fb33f6daf.json", "report": "/leaderboard/reports/hm-c0b594469a7fb33f6daf.md", "plan": "/leaderboard/plans/hm-c0b594469a7fb33f6daf.md" }, { "id": "hm-c16ec95138b047cfe5ea", "model_label": "Grok 4 Fast", "lab": "xAI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c16ec95138b047cfe5ea.json", "report": "/leaderboard/reports/hm-c16ec95138b047cfe5ea.md", "plan": "/leaderboard/plans/hm-c16ec95138b047cfe5ea.md" }, { "id": "hm-c1855d486a329836af7c", "model_label": "deepseek-v3", "lab": "DeepSeek", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c1855d486a329836af7c.json", "report": "/leaderboard/reports/hm-c1855d486a329836af7c.md", "plan": "/leaderboard/plans/hm-c1855d486a329836af7c.md" }, { "id": "hm-c226397a30aa9c874dc5", "model_label": "claude-3-opus-20240229", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c226397a30aa9c874dc5.json", "report": "/leaderboard/reports/hm-c226397a30aa9c874dc5.md", "plan": "/leaderboard/plans/hm-c226397a30aa9c874dc5.md" }, { "id": "hm-c2f735847fc93cef455b", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c2f735847fc93cef455b.json", "report": "/leaderboard/reports/hm-c2f735847fc93cef455b.md", "plan": "/leaderboard/plans/hm-c2f735847fc93cef455b.md" }, { "id": "hm-c3586457e2f7c06533ed", "model_label": "qwen/qwen3.8-max-prime", "lab": "Alibaba / Qwen", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c3586457e2f7c06533ed.json", "report": "/leaderboard/reports/hm-c3586457e2f7c06533ed.md", "plan": "/leaderboard/plans/hm-c3586457e2f7c06533ed.md" }, { "id": "hm-c41555b290c3645d52fa", "model_label": "GPT-4o", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c41555b290c3645d52fa.json", "report": "/leaderboard/reports/hm-c41555b290c3645d52fa.md", "plan": "/leaderboard/plans/hm-c41555b290c3645d52fa.md" }, { "id": "hm-c430dbc8259efbed18a2", "model_label": "llama2-chat-70b", "lab": "Meta", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c430dbc8259efbed18a2.json", "report": "/leaderboard/reports/hm-c430dbc8259efbed18a2.md", "plan": "/leaderboard/plans/hm-c430dbc8259efbed18a2.md" }, { "id": "hm-c46fd22a84c0a2812805", "model_label": "Qwen3-235B-A22B-Thinking-2507", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c46fd22a84c0a2812805.json", "report": "/leaderboard/reports/hm-c46fd22a84c0a2812805.md", "plan": "/leaderboard/plans/hm-c46fd22a84c0a2812805.md" }, { "id": "hm-c4b8656ef5812550ca1d", "model_label": "gpt-4.5-preview-2025-02-27", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c4b8656ef5812550ca1d.json", "report": "/leaderboard/reports/hm-c4b8656ef5812550ca1d.md", "plan": "/leaderboard/plans/hm-c4b8656ef5812550ca1d.md" }, { "id": "hm-c4e39f53bef4c54cf763", "model_label": "MiniMaxAI/minimax-m2p1", "lab": "MiniMax", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c4e39f53bef4c54cf763.json", "report": "/leaderboard/reports/hm-c4e39f53bef4c54cf763.md", "plan": "/leaderboard/plans/hm-c4e39f53bef4c54cf763.md" }, { "id": "hm-c5693a4051f4ef3f0128", "model_label": "anthropic/claude-fable-5.1", "lab": "Anthropic", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c5693a4051f4ef3f0128.json", "report": "/leaderboard/reports/hm-c5693a4051f4ef3f0128.md", "plan": "/leaderboard/plans/hm-c5693a4051f4ef3f0128.md" }, { "id": "hm-c61db46a22b21dcaac62", "model_label": "qwen/qwen3.5-35b-a3b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c61db46a22b21dcaac62.json", "report": "/leaderboard/reports/hm-c61db46a22b21dcaac62.md", "plan": "/leaderboard/plans/hm-c61db46a22b21dcaac62.md" }, { "id": "hm-c67b0f55889c5442548e", "model_label": "O1", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c67b0f55889c5442548e.json", "report": "/leaderboard/reports/hm-c67b0f55889c5442548e.md", "plan": "/leaderboard/plans/hm-c67b0f55889c5442548e.md" }, { "id": "hm-c6930d2603267a01f13a", "model_label": "gpt-4o-2024-08-06", "lab": "OpenAI", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c6930d2603267a01f13a.json", "report": "/leaderboard/reports/hm-c6930d2603267a01f13a.md", "plan": "/leaderboard/plans/hm-c6930d2603267a01f13a.md" }, { "id": "hm-c6bd8e309514d0770420", "model_label": "Kimi K2 Thinking", "lab": "Moonshot AI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c6bd8e309514d0770420.json", "report": "/leaderboard/reports/hm-c6bd8e309514d0770420.md", "plan": "/leaderboard/plans/hm-c6bd8e309514d0770420.md" }, { "id": "hm-c73479675986d832562b", "model_label": "o1-preview", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c73479675986d832562b.json", "report": "/leaderboard/reports/hm-c73479675986d832562b.md", "plan": "/leaderboard/plans/hm-c73479675986d832562b.md" }, { "id": "hm-c7369a153df1153d8cab", "model_label": "snowflake/snowflake-arctic-instruct", "lab": "Snowflake", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c7369a153df1153d8cab.json", "report": "/leaderboard/reports/hm-c7369a153df1153d8cab.md", "plan": "/leaderboard/plans/hm-c7369a153df1153d8cab.md" }, { "id": "hm-c77cccdc648b34618637", "model_label": "gpt-4.1-2025-04-14", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c77cccdc648b34618637.json", "report": "/leaderboard/reports/hm-c77cccdc648b34618637.md", "plan": "/leaderboard/plans/hm-c77cccdc648b34618637.md" }, { "id": "hm-c8a86409ac400fb59a88", "model_label": "anthropic/claude-opus-4-6", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-c8a86409ac400fb59a88.json", "report": "/leaderboard/reports/hm-c8a86409ac400fb59a88.md", "plan": "/leaderboard/plans/hm-c8a86409ac400fb59a88.md" }, { "id": "hm-ca3ea5571022910f3a9e", "model_label": "GPT-5 mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ca3ea5571022910f3a9e.json", "report": "/leaderboard/reports/hm-ca3ea5571022910f3a9e.md", "plan": "/leaderboard/plans/hm-ca3ea5571022910f3a9e.md" }, { "id": "hm-cb6c87d18884583cf445", "model_label": "deepseek-ai/DeepSeek-V4-Pro", "lab": "DeepSeek", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cb6c87d18884583cf445.json", "report": "/leaderboard/reports/hm-cb6c87d18884583cf445.md", "plan": "/leaderboard/plans/hm-cb6c87d18884583cf445.md" }, { "id": "hm-cc88be6a5e7bc260d275", "model_label": "Claude-3 Sonnet", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cc88be6a5e7bc260d275.json", "report": "/leaderboard/reports/hm-cc88be6a5e7bc260d275.md", "plan": "/leaderboard/plans/hm-cc88be6a5e7bc260d275.md" }, { "id": "hm-ccbaf198bf723c4c6ff1", "model_label": "Claude Sonnet 4", "lab": "Anthropic", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ccbaf198bf723c4c6ff1.json", "report": "/leaderboard/reports/hm-ccbaf198bf723c4c6ff1.md", "plan": "/leaderboard/plans/hm-ccbaf198bf723c4c6ff1.md" }, { "id": "hm-cd0b1da718db2823181e", "model_label": "DeepSeek V3.2 Exp", "lab": "DeepSeek", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cd0b1da718db2823181e.json", "report": "/leaderboard/reports/hm-cd0b1da718db2823181e.md", "plan": "/leaderboard/plans/hm-cd0b1da718db2823181e.md" }, { "id": "hm-cd295c3964939eb556a4", "model_label": "Mistral-7B-Instruct-v0.3", "lab": "Mistral AI", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cd295c3964939eb556a4.json", "report": "/leaderboard/reports/hm-cd295c3964939eb556a4.md", "plan": "/leaderboard/plans/hm-cd295c3964939eb556a4.md" }, { "id": "hm-cdd75008651163b88b6e", "model_label": "anthropic/claude-opus-4-5-20251101", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cdd75008651163b88b6e.json", "report": "/leaderboard/reports/hm-cdd75008651163b88b6e.md", "plan": "/leaderboard/plans/hm-cdd75008651163b88b6e.md" }, { "id": "hm-ce95fcf1e83d45594d2e", "model_label": "moonshotai/kimi-k3", "lab": "Moonshot AI", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ce95fcf1e83d45594d2e.json", "report": "/leaderboard/reports/hm-ce95fcf1e83d45594d2e.md", "plan": "/leaderboard/plans/hm-ce95fcf1e83d45594d2e.md" }, { "id": "hm-ceecbe207c65d159151d", "model_label": "claude-haiku-4-5-20251001", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ceecbe207c65d159151d.json", "report": "/leaderboard/reports/hm-ceecbe207c65d159151d.md", "plan": "/leaderboard/plans/hm-ceecbe207c65d159151d.md" }, { "id": "hm-cf32fffd339cc95230bd", "model_label": "Kimi k2 Thinking", "lab": "Moonshot AI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cf32fffd339cc95230bd.json", "report": "/leaderboard/reports/hm-cf32fffd339cc95230bd.md", "plan": "/leaderboard/plans/hm-cf32fffd339cc95230bd.md" }, { "id": "hm-cf3eef58fc02575f0fb4", "model_label": "kimi-k2.7-code", "lab": "Moonshot", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cf3eef58fc02575f0fb4.json", "report": "/leaderboard/reports/hm-cf3eef58fc02575f0fb4.md", "plan": "/leaderboard/plans/hm-cf3eef58fc02575f0fb4.md" }, { "id": "hm-cfa29f7740811f3296eb", "model_label": "Claude-3 Sonnet", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-cfa29f7740811f3296eb.json", "report": "/leaderboard/reports/hm-cfa29f7740811f3296eb.md", "plan": "/leaderboard/plans/hm-cfa29f7740811f3296eb.md" }, { "id": "hm-d0285922feb26d0e01b3", "model_label": "qwen3.6-flash", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d0285922feb26d0e01b3.json", "report": "/leaderboard/reports/hm-d0285922feb26d0e01b3.md", "plan": "/leaderboard/plans/hm-d0285922feb26d0e01b3.md" }, { "id": "hm-d02a59da4f7173f97155", "model_label": "Llama-3 Instruct (70B)", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d02a59da4f7173f97155.json", "report": "/leaderboard/reports/hm-d02a59da4f7173f97155.md", "plan": "/leaderboard/plans/hm-d02a59da4f7173f97155.md" }, { "id": "hm-d0998fb61297d7a10a2d", "model_label": "gpt-4o-2024-05-13", "lab": "OpenAI", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d0998fb61297d7a10a2d.json", "report": "/leaderboard/reports/hm-d0998fb61297d7a10a2d.md", "plan": "/leaderboard/plans/hm-d0998fb61297d7a10a2d.md" }, { "id": "hm-d09f85d11d42bd905289", "model_label": "gemma-2-27b-it", "lab": "Google", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d09f85d11d42bd905289.json", "report": "/leaderboard/reports/hm-d09f85d11d42bd905289.md", "plan": "/leaderboard/plans/hm-d09f85d11d42bd905289.md" }, { "id": "hm-d0bac822deaaf3d0b593", "model_label": "google/gemma-4-26b-a4b-it", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d0bac822deaaf3d0b593.json", "report": "/leaderboard/reports/hm-d0bac822deaaf3d0b593.md", "plan": "/leaderboard/plans/hm-d0bac822deaaf3d0b593.md" }, { "id": "hm-d0fc4523badb0806809d", "model_label": "mistralai/mistral-3-large-2512", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d0fc4523badb0806809d.json", "report": "/leaderboard/reports/hm-d0fc4523badb0806809d.md", "plan": "/leaderboard/plans/hm-d0fc4523badb0806809d.md" }, { "id": "hm-d20a145462d62deaa2e4", "model_label": "Claude 3.5 Sonnet", "lab": "Anthropic", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d20a145462d62deaa2e4.json", "report": "/leaderboard/reports/hm-d20a145462d62deaa2e4.md", "plan": "/leaderboard/plans/hm-d20a145462d62deaa2e4.md" }, { "id": "hm-d420cc53f4dff0e875b2", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d420cc53f4dff0e875b2.json", "report": "/leaderboard/reports/hm-d420cc53f4dff0e875b2.md", "plan": "/leaderboard/plans/hm-d420cc53f4dff0e875b2.md" }, { "id": "hm-d4587ee1eeeb8ed0fc0c", "model_label": "Gemini 2.5 Flash", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d4587ee1eeeb8ed0fc0c.json", "report": "/leaderboard/reports/hm-d4587ee1eeeb8ed0fc0c.md", "plan": "/leaderboard/plans/hm-d4587ee1eeeb8ed0fc0c.md" }, { "id": "hm-d4bf1fcafb9c94748886", "model_label": "Claude Opus 4.1", "lab": "Anthropic", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d4bf1fcafb9c94748886.json", "report": "/leaderboard/reports/hm-d4bf1fcafb9c94748886.md", "plan": "/leaderboard/plans/hm-d4bf1fcafb9c94748886.md" }, { "id": "hm-d54eb3e317fbefb4b564", "model_label": "claude-opus-5_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d54eb3e317fbefb4b564.json", "report": "/leaderboard/reports/hm-d54eb3e317fbefb4b564.md", "plan": "/leaderboard/plans/hm-d54eb3e317fbefb4b564.md" }, { "id": "hm-d702e017a71dd20f542b", "model_label": "gemini-4-argon_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d702e017a71dd20f542b.json", "report": "/leaderboard/reports/hm-d702e017a71dd20f542b.md", "plan": "/leaderboard/plans/hm-d702e017a71dd20f542b.md" }, { "id": "hm-d86fc0b36be9762a715e", "model_label": "Gemini 3 Pro Preview", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-d86fc0b36be9762a715e.json", "report": "/leaderboard/reports/hm-d86fc0b36be9762a715e.md", "plan": "/leaderboard/plans/hm-d86fc0b36be9762a715e.md" }, { "id": "hm-da259aa1fe69dcdfd6da", "model_label": "claude-3-7-sonnet-20250219", "lab": "Anthropic", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-da259aa1fe69dcdfd6da.json", "report": "/leaderboard/reports/hm-da259aa1fe69dcdfd6da.md", "plan": "/leaderboard/plans/hm-da259aa1fe69dcdfd6da.md" }, { "id": "hm-da61a0fced28625ad439", "model_label": "openai/gpt-5-minimal-2025-08-07", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-da61a0fced28625ad439.json", "report": "/leaderboard/reports/hm-da61a0fced28625ad439.md", "plan": "/leaderboard/plans/hm-da61a0fced28625ad439.md" }, { "id": "hm-da6e2d53ae949baa410a", "model_label": "openai/gpt-5.1-high-2025-11-13", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-da6e2d53ae949baa410a.json", "report": "/leaderboard/reports/hm-da6e2d53ae949baa410a.md", "plan": "/leaderboard/plans/hm-da6e2d53ae949baa410a.md" }, { "id": "hm-daaa3b2b356c0780841b", "model_label": "Gemini 1.5 Pro", "lab": "Google", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-daaa3b2b356c0780841b.json", "report": "/leaderboard/reports/hm-daaa3b2b356c0780841b.md", "plan": "/leaderboard/plans/hm-daaa3b2b356c0780841b.md" }, { "id": "hm-db661b3e7fd977c8dd90", "model_label": "qwen3.8-max_xhigh", "lab": "Alibaba", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-db661b3e7fd977c8dd90.json", "report": "/leaderboard/reports/hm-db661b3e7fd977c8dd90.md", "plan": "/leaderboard/plans/hm-db661b3e7fd977c8dd90.md" }, { "id": "hm-db7d1f20c13e6c5b5f58", "model_label": "qwen25-05b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-db7d1f20c13e6c5b5f58.json", "report": "/leaderboard/reports/hm-db7d1f20c13e6c5b5f58.md", "plan": "/leaderboard/plans/hm-db7d1f20c13e6c5b5f58.md" }, { "id": "hm-dbe995ad19fe2544e9a0", "model_label": "gpt-5.4-mini-2026-03-17_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-dbe995ad19fe2544e9a0.json", "report": "/leaderboard/reports/hm-dbe995ad19fe2544e9a0.md", "plan": "/leaderboard/plans/hm-dbe995ad19fe2544e9a0.md" }, { "id": "hm-dc3bfdb112c6b55ae8b4", "model_label": "qwen/qwen3.5-27b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-dc3bfdb112c6b55ae8b4.json", "report": "/leaderboard/reports/hm-dc3bfdb112c6b55ae8b4.md", "plan": "/leaderboard/plans/hm-dc3bfdb112c6b55ae8b4.md" }, { "id": "hm-dc6630123ccd69a9ba14", "model_label": "moonshotai/Kimi-K2-Instruct-0905", "lab": "Moonshot AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-dc6630123ccd69a9ba14.json", "report": "/leaderboard/reports/hm-dc6630123ccd69a9ba14.md", "plan": "/leaderboard/plans/hm-dc6630123ccd69a9ba14.md" }, { "id": "hm-dc774967d69d573be6da", "model_label": "openai/gpt-6-sol", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-dc774967d69d573be6da.json", "report": "/leaderboard/reports/hm-dc774967d69d573be6da.md", "plan": "/leaderboard/plans/hm-dc774967d69d573be6da.md" }, { "id": "hm-dcbb99ee1946aa596d0c", "model_label": "gpt-5.6-terra_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-dcbb99ee1946aa596d0c.json", "report": "/leaderboard/reports/hm-dcbb99ee1946aa596d0c.md", "plan": "/leaderboard/plans/hm-dcbb99ee1946aa596d0c.md" }, { "id": "hm-ddff5a9aa1da82215ede", "model_label": "gpt-4.5-preview-2025-02-27", "lab": "OpenAI", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ddff5a9aa1da82215ede.json", "report": "/leaderboard/reports/hm-ddff5a9aa1da82215ede.md", "plan": "/leaderboard/plans/hm-ddff5a9aa1da82215ede.md" }, { "id": "hm-deb017d037da5857f977", "model_label": "gpt-5.1-2025-11-13_high", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-deb017d037da5857f977.json", "report": "/leaderboard/reports/hm-deb017d037da5857f977.md", "plan": "/leaderboard/plans/hm-deb017d037da5857f977.md" }, { "id": "hm-df2d2e22a44b663d1e47", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-df2d2e22a44b663d1e47.json", "report": "/leaderboard/reports/hm-df2d2e22a44b663d1e47.md", "plan": "/leaderboard/plans/hm-df2d2e22a44b663d1e47.md" }, { "id": "hm-df695359d1b743fd956c", "model_label": "qwen25-3b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-df695359d1b743fd956c.json", "report": "/leaderboard/reports/hm-df695359d1b743fd956c.md", "plan": "/leaderboard/plans/hm-df695359d1b743fd956c.md" }, { "id": "hm-df8a5bf6deed44ebcb29", "model_label": "gpt-oss-120B (high)", "lab": "OpenAI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-df8a5bf6deed44ebcb29.json", "report": "/leaderboard/reports/hm-df8a5bf6deed44ebcb29.md", "plan": "/leaderboard/plans/hm-df8a5bf6deed44ebcb29.md" }, { "id": "hm-e02684d18aad24453d93", "model_label": "gpt-3.5-turbo-0125", "lab": "OpenAI", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e02684d18aad24453d93.json", "report": "/leaderboard/reports/hm-e02684d18aad24453d93.md", "plan": "/leaderboard/plans/hm-e02684d18aad24453d93.md" }, { "id": "hm-e040b1bd83b193c8101b", "model_label": "GPT-4 Turbo", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e040b1bd83b193c8101b.json", "report": "/leaderboard/reports/hm-e040b1bd83b193c8101b.md", "plan": "/leaderboard/plans/hm-e040b1bd83b193c8101b.md" }, { "id": "hm-e177528b4317d4a0197d", "model_label": "google/gemini-2.5-pro", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e177528b4317d4a0197d.json", "report": "/leaderboard/reports/hm-e177528b4317d4a0197d.md", "plan": "/leaderboard/plans/hm-e177528b4317d4a0197d.md" }, { "id": "hm-e19ac3f345665f221b38", "model_label": "Command R+", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e19ac3f345665f221b38.json", "report": "/leaderboard/reports/hm-e19ac3f345665f221b38.md", "plan": "/leaderboard/plans/hm-e19ac3f345665f221b38.md" }, { "id": "hm-e1e7a6ed6d19585c9532", "model_label": "qwq-32b-preview", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e1e7a6ed6d19585c9532.json", "report": "/leaderboard/reports/hm-e1e7a6ed6d19585c9532.md", "plan": "/leaderboard/plans/hm-e1e7a6ed6d19585c9532.md" }, { "id": "hm-e28f891d1fbc98fdc45a", "model_label": "GPT-5 Low", "lab": "OpenAI", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e28f891d1fbc98fdc45a.json", "report": "/leaderboard/reports/hm-e28f891d1fbc98fdc45a.md", "plan": "/leaderboard/plans/hm-e28f891d1fbc98fdc45a.md" }, { "id": "hm-e35e654be581bec0e1f1", "model_label": "Gemini 3.1 Pro", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e35e654be581bec0e1f1.json", "report": "/leaderboard/reports/hm-e35e654be581bec0e1f1.md", "plan": "/leaderboard/plans/hm-e35e654be581bec0e1f1.md" }, { "id": "hm-e382751e0731d6deb37e", "model_label": "GPT-4 Turbo", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e382751e0731d6deb37e.json", "report": "/leaderboard/reports/hm-e382751e0731d6deb37e.md", "plan": "/leaderboard/plans/hm-e382751e0731d6deb37e.md" }, { "id": "hm-e3c2eda888c12a056f32", "model_label": "moonshotai/kimi-k2.6", "lab": "Moonshot AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e3c2eda888c12a056f32.json", "report": "/leaderboard/reports/hm-e3c2eda888c12a056f32.md", "plan": "/leaderboard/plans/hm-e3c2eda888c12a056f32.md" }, { "id": "hm-e457486daf8cd56314c2", "model_label": "GPT-3 175B", "lab": "OpenAI", "source": "truthfulqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e457486daf8cd56314c2.json", "report": "/leaderboard/reports/hm-e457486daf8cd56314c2.md", "plan": "/leaderboard/plans/hm-e457486daf8cd56314c2.md" }, { "id": "hm-e4a608ad09cdec341a09", "model_label": "mistralai/ministral-3b-2410", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e4a608ad09cdec341a09.json", "report": "/leaderboard/reports/hm-e4a608ad09cdec341a09.md", "plan": "/leaderboard/plans/hm-e4a608ad09cdec341a09.md" }, { "id": "hm-e57af43af9886261cfbc", "model_label": "GPT-2 1.5B", "lab": "OpenAI", "source": "truthfulqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e57af43af9886261cfbc.json", "report": "/leaderboard/reports/hm-e57af43af9886261cfbc.md", "plan": "/leaderboard/plans/hm-e57af43af9886261cfbc.md" }, { "id": "hm-e61fcb3cf73386bb3ef9", "model_label": "MiniMaxAI/minimax-m2p5", "lab": "MiniMax", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e61fcb3cf73386bb3ef9.json", "report": "/leaderboard/reports/hm-e61fcb3cf73386bb3ef9.md", "plan": "/leaderboard/plans/hm-e61fcb3cf73386bb3ef9.md" }, { "id": "hm-e681ed9834f266459f76", "model_label": "openai/gpt-5.1-low-2025-11-13", "lab": "OpenAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e681ed9834f266459f76.json", "report": "/leaderboard/reports/hm-e681ed9834f266459f76.md", "plan": "/leaderboard/plans/hm-e681ed9834f266459f76.md" }, { "id": "hm-e6a571ad1120a4e76c13", "model_label": "Claude Opus 4.1", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e6a571ad1120a4e76c13.json", "report": "/leaderboard/reports/hm-e6a571ad1120a4e76c13.md", "plan": "/leaderboard/plans/hm-e6a571ad1120a4e76c13.md" }, { "id": "hm-e746a81f5451f9de5263", "model_label": "Gemini 3.1 Pro Preview", "lab": "Google", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e746a81f5451f9de5263.json", "report": "/leaderboard/reports/hm-e746a81f5451f9de5263.md", "plan": "/leaderboard/plans/hm-e746a81f5451f9de5263.md" }, { "id": "hm-e866858ff241b1eb6dc6", "model_label": "o3", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e866858ff241b1eb6dc6.json", "report": "/leaderboard/reports/hm-e866858ff241b1eb6dc6.md", "plan": "/leaderboard/plans/hm-e866858ff241b1eb6dc6.md" }, { "id": "hm-e87726e7ac102cfc9715", "model_label": "deepseek-v4.1-flash_max", "lab": "DeepSeek", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e87726e7ac102cfc9715.json", "report": "/leaderboard/reports/hm-e87726e7ac102cfc9715.md", "plan": "/leaderboard/plans/hm-e87726e7ac102cfc9715.md" }, { "id": "hm-e891ddd39a78e29cee51", "model_label": "LLaMA-13B", "lab": "Meta", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e891ddd39a78e29cee51.json", "report": "/leaderboard/reports/hm-e891ddd39a78e29cee51.md", "plan": "/leaderboard/plans/hm-e891ddd39a78e29cee51.md" }, { "id": "hm-e8e7a53aaca4922c417f", "model_label": "deepseek-llm-67b-chat", "lab": "DeepSeek", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e8e7a53aaca4922c417f.json", "report": "/leaderboard/reports/hm-e8e7a53aaca4922c417f.md", "plan": "/leaderboard/plans/hm-e8e7a53aaca4922c417f.md" }, { "id": "hm-e9a0a6219244c7ae4918", "model_label": "xai-org/grok-4-1-fast-reasoning", "lab": "xAI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-e9a0a6219244c7ae4918.json", "report": "/leaderboard/reports/hm-e9a0a6219244c7ae4918.md", "plan": "/leaderboard/plans/hm-e9a0a6219244c7ae4918.md" }, { "id": "hm-ea2bf728602b617a68da", "model_label": "deepseek-ai/DeepSeek-V3.1", "lab": "DeepSeek", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ea2bf728602b617a68da.json", "report": "/leaderboard/reports/hm-ea2bf728602b617a68da.md", "plan": "/leaderboard/plans/hm-ea2bf728602b617a68da.md" }, { "id": "hm-ea4479b2cbd0c616982b", "model_label": "Claude Sonnet 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ea4479b2cbd0c616982b.json", "report": "/leaderboard/reports/hm-ea4479b2cbd0c616982b.md", "plan": "/leaderboard/plans/hm-ea4479b2cbd0c616982b.md" }, { "id": "hm-eaf48aa82f30591be19b", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-eaf48aa82f30591be19b.json", "report": "/leaderboard/reports/hm-eaf48aa82f30591be19b.md", "plan": "/leaderboard/plans/hm-eaf48aa82f30591be19b.md" }, { "id": "hm-eb66b7183bcd8810328a", "model_label": "amazon/nova-pro-v1:0", "lab": "Amazon", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-eb66b7183bcd8810328a.json", "report": "/leaderboard/reports/hm-eb66b7183bcd8810328a.md", "plan": "/leaderboard/plans/hm-eb66b7183bcd8810328a.md" }, { "id": "hm-ec006c2883b9e4f6edea", "model_label": "ibm-granite/granite-3.3-8b-instruct", "lab": "IBM", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ec006c2883b9e4f6edea.json", "report": "/leaderboard/reports/hm-ec006c2883b9e4f6edea.md", "plan": "/leaderboard/plans/hm-ec006c2883b9e4f6edea.md" }, { "id": "hm-ec5563da1484e450d784", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "confidencebench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ec5563da1484e450d784.json", "report": "/leaderboard/reports/hm-ec5563da1484e450d784.md", "plan": "/leaderboard/plans/hm-ec5563da1484e450d784.md" }, { "id": "hm-ed05aea914470fc4708f", "model_label": "anthropic/claude-sonnet-4-6", "lab": "Anthropic", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ed05aea914470fc4708f.json", "report": "/leaderboard/reports/hm-ed05aea914470fc4708f.md", "plan": "/leaderboard/plans/hm-ed05aea914470fc4708f.md" }, { "id": "hm-edbe9940ecc525240025", "model_label": "GPT-3.5 Turbo", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-edbe9940ecc525240025.json", "report": "/leaderboard/reports/hm-edbe9940ecc525240025.md", "plan": "/leaderboard/plans/hm-edbe9940ecc525240025.md" }, { "id": "hm-ee553aa358bea3f492a6", "model_label": "Gemini 3 Pro Preview", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ee553aa358bea3f492a6.json", "report": "/leaderboard/reports/hm-ee553aa358bea3f492a6.md", "plan": "/leaderboard/plans/hm-ee553aa358bea3f492a6.md" }, { "id": "hm-efe3cd4cb833bf2c7fb3", "model_label": "arcee-ai/trinity-large-preview", "lab": "Arcee AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-efe3cd4cb833bf2c7fb3.json", "report": "/leaderboard/reports/hm-efe3cd4cb833bf2c7fb3.md", "plan": "/leaderboard/plans/hm-efe3cd4cb833bf2c7fb3.md" }, { "id": "hm-f14d050bc015c86d10e1", "model_label": "GPT-5 (high)", "lab": "OpenAI", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f14d050bc015c86d10e1.json", "report": "/leaderboard/reports/hm-f14d050bc015c86d10e1.md", "plan": "/leaderboard/plans/hm-f14d050bc015c86d10e1.md" }, { "id": "hm-f1dd91e80dc1ce0756b7", "model_label": "qwen/qwen3.5-122b-a10b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f1dd91e80dc1ce0756b7.json", "report": "/leaderboard/reports/hm-f1dd91e80dc1ce0756b7.md", "plan": "/leaderboard/plans/hm-f1dd91e80dc1ce0756b7.md" }, { "id": "hm-f29cff8dc449dba37e10", "model_label": "o4-mini", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f29cff8dc449dba37e10.json", "report": "/leaderboard/reports/hm-f29cff8dc449dba37e10.md", "plan": "/leaderboard/plans/hm-f29cff8dc449dba37e10.md" }, { "id": "hm-f35f5772ab0d7e72a185", "model_label": "glm-4.7", "lab": "Z.ai (Zhipu AI)", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f35f5772ab0d7e72a185.json", "report": "/leaderboard/reports/hm-f35f5772ab0d7e72a185.md", "plan": "/leaderboard/plans/hm-f35f5772ab0d7e72a185.md" }, { "id": "hm-f477e055c6c37d461169", "model_label": "claude-sonnet-5_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f477e055c6c37d461169.json", "report": "/leaderboard/reports/hm-f477e055c6c37d461169.md", "plan": "/leaderboard/plans/hm-f477e055c6c37d461169.md" }, { "id": "hm-f5337890aeb89d2aa7e4", "model_label": "claude-sonnet-5-5_max", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f5337890aeb89d2aa7e4.json", "report": "/leaderboard/reports/hm-f5337890aeb89d2aa7e4.md", "plan": "/leaderboard/plans/hm-f5337890aeb89d2aa7e4.md" }, { "id": "hm-f5479aec5ce6f48b8ac2", "model_label": "llama2-chat-7b", "lab": "Meta", "source": "behonest", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f5479aec5ce6f48b8ac2.json", "report": "/leaderboard/reports/hm-f5479aec5ce6f48b8ac2.md", "plan": "/leaderboard/plans/hm-f5479aec5ce6f48b8ac2.md" }, { "id": "hm-f5a3fda94507a5b415fe", "model_label": "gpt-5.6-luna_max", "lab": "OpenAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f5a3fda94507a5b415fe.json", "report": "/leaderboard/reports/hm-f5a3fda94507a5b415fe.md", "plan": "/leaderboard/plans/hm-f5a3fda94507a5b415fe.md" }, { "id": "hm-f6f90e1aa145bfa75796", "model_label": "Gemini 3 Pro Preview", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f6f90e1aa145bfa75796.json", "report": "/leaderboard/reports/hm-f6f90e1aa145bfa75796.md", "plan": "/leaderboard/plans/hm-f6f90e1aa145bfa75796.md" }, { "id": "hm-f74df19cc5418bd47578", "model_label": "qwen/qwen3-235b-a22b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f74df19cc5418bd47578.json", "report": "/leaderboard/reports/hm-f74df19cc5418bd47578.md", "plan": "/leaderboard/plans/hm-f74df19cc5418bd47578.md" }, { "id": "hm-f78363a8b4a8b07cb42f", "model_label": "openai/gpt-6.1-sol", "lab": "OpenAI", "source": "honesty", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f78363a8b4a8b07cb42f.json", "report": "/leaderboard/reports/hm-f78363a8b4a8b07cb42f.md", "plan": "/leaderboard/plans/hm-f78363a8b4a8b07cb42f.md" }, { "id": "hm-f7d27824fc54b0bf0332", "model_label": "moonshotai/Kimi-K2.5", "lab": "Moonshot AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f7d27824fc54b0bf0332.json", "report": "/leaderboard/reports/hm-f7d27824fc54b0bf0332.md", "plan": "/leaderboard/plans/hm-f7d27824fc54b0bf0332.md" }, { "id": "hm-f7f8a39a002a33e645e6", "model_label": "qwen15-72b-chat", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f7f8a39a002a33e645e6.json", "report": "/leaderboard/reports/hm-f7f8a39a002a33e645e6.md", "plan": "/leaderboard/plans/hm-f7f8a39a002a33e645e6.md" }, { "id": "hm-f88aadd2968dc59601f8", "model_label": "gpt-4o-mini", "lab": "OpenAI", "source": "faitheval", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f88aadd2968dc59601f8.json", "report": "/leaderboard/reports/hm-f88aadd2968dc59601f8.md", "plan": "/leaderboard/plans/hm-f88aadd2968dc59601f8.md" }, { "id": "hm-f8ad1f61c64e0d95a39c", "model_label": "gpt-4.1-nano-2025-04-14", "lab": "OpenAI", "source": "simpleqa", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f8ad1f61c64e0d95a39c.json", "report": "/leaderboard/reports/hm-f8ad1f61c64e0d95a39c.md", "plan": "/leaderboard/plans/hm-f8ad1f61c64e0d95a39c.md" }, { "id": "hm-f8d77b4eefbd75f385cc", "model_label": "gemini-3.5-flash_high", "lab": "Google DeepMind", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f8d77b4eefbd75f385cc.json", "report": "/leaderboard/reports/hm-f8d77b4eefbd75f385cc.md", "plan": "/leaderboard/plans/hm-f8d77b4eefbd75f385cc.md" }, { "id": "hm-f8e66979c11dcc0980ee", "model_label": "GPT-OSS-120B", "lab": "OpenAI", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f8e66979c11dcc0980ee.json", "report": "/leaderboard/reports/hm-f8e66979c11dcc0980ee.md", "plan": "/leaderboard/plans/hm-f8e66979c11dcc0980ee.md" }, { "id": "hm-f8e980b52c4736270237", "model_label": "o1", "lab": "OpenAI", "source": "abstentionbench", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f8e980b52c4736270237.json", "report": "/leaderboard/reports/hm-f8e980b52c4736270237.md", "plan": "/leaderboard/plans/hm-f8e980b52c4736270237.md" }, { "id": "hm-f97890ef93e6828cae74", "model_label": "Deepseek V3", "lab": "DeepSeek", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f97890ef93e6828cae74.json", "report": "/leaderboard/reports/hm-f97890ef93e6828cae74.md", "plan": "/leaderboard/plans/hm-f97890ef93e6828cae74.md" }, { "id": "hm-f97a1f247fe4e3eb8117", "model_label": "deepseek-v4-pro-0813_max", "lab": "DeepSeek", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f97a1f247fe4e3eb8117.json", "report": "/leaderboard/reports/hm-f97a1f247fe4e3eb8117.md", "plan": "/leaderboard/plans/hm-f97a1f247fe4e3eb8117.md" }, { "id": "hm-f9adfcc689d10d724e22", "model_label": "Qwen3 Next 80B A3B", "lab": "Alibaba", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-f9adfcc689d10d724e22.json", "report": "/leaderboard/reports/hm-f9adfcc689d10d724e22.md", "plan": "/leaderboard/plans/hm-f9adfcc689d10d724e22.md" }, { "id": "hm-fac8569dba2e747fcfc2", "model_label": "GPT-4o Mini", "lab": "OpenAI", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fac8569dba2e747fcfc2.json", "report": "/leaderboard/reports/hm-fac8569dba2e747fcfc2.md", "plan": "/leaderboard/plans/hm-fac8569dba2e747fcfc2.md" }, { "id": "hm-facbc473c4747ce2ef97", "model_label": "Claude Opus 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-facbc473c4747ce2ef97.json", "report": "/leaderboard/reports/hm-facbc473c4747ce2ef97.md", "plan": "/leaderboard/plans/hm-facbc473c4747ce2ef97.md" }, { "id": "hm-fae26be12c22743357d6", "model_label": "Inkling_xhigh", "lab": "Thinking Machines", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fae26be12c22743357d6.json", "report": "/leaderboard/reports/hm-fae26be12c22743357d6.md", "plan": "/leaderboard/plans/hm-fae26be12c22743357d6.md" }, { "id": "hm-fb4ea30c138ab097c0a4", "model_label": "Mixtral (8x22B)", "lab": null, "source": "belief_r", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fb4ea30c138ab097c0a4.json", "report": "/leaderboard/reports/hm-fb4ea30c138ab097c0a4.md", "plan": "/leaderboard/plans/hm-fb4ea30c138ab097c0a4.md" }, { "id": "hm-fb8e985157f4cf606b4d", "model_label": "qwen/qwen3-4b", "lab": "Alibaba / Qwen", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fb8e985157f4cf606b4d.json", "report": "/leaderboard/reports/hm-fb8e985157f4cf606b4d.md", "plan": "/leaderboard/plans/hm-fb8e985157f4cf606b4d.md" }, { "id": "hm-fc608511fb2445e094d4", "model_label": "claude-haiku-4-5-20251001_32K", "lab": "Anthropic", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fc608511fb2445e094d4.json", "report": "/leaderboard/reports/hm-fc608511fb2445e094d4.md", "plan": "/leaderboard/plans/hm-fc608511fb2445e094d4.md" }, { "id": "hm-fd49a772c972edad1c9e", "model_label": "Claude 3.5 Haiku", "lab": "Anthropic", "source": "hal", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fd49a772c972edad1c9e.json", "report": "/leaderboard/reports/hm-fd49a772c972edad1c9e.md", "plan": "/leaderboard/plans/hm-fd49a772c972edad1c9e.md" }, { "id": "hm-fdccd153e660de22c045", "model_label": "llama-2-13b-chat", "lab": "Meta", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fdccd153e660de22c045.json", "report": "/leaderboard/reports/hm-fdccd153e660de22c045.md", "plan": "/leaderboard/plans/hm-fdccd153e660de22c045.md" }, { "id": "hm-fdd2b32aff77a6d4f162", "model_label": "google/gemini-3-flash-preview", "lab": "Google", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fdd2b32aff77a6d4f162.json", "report": "/leaderboard/reports/hm-fdd2b32aff77a6d4f162.md", "plan": "/leaderboard/plans/hm-fdd2b32aff77a6d4f162.md" }, { "id": "hm-fe23cfb45cd2719056f0", "model_label": "MiniMax-M2", "lab": "MiniMax", "source": "aa_omniscience", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fe23cfb45cd2719056f0.json", "report": "/leaderboard/reports/hm-fe23cfb45cd2719056f0.md", "plan": "/leaderboard/plans/hm-fe23cfb45cd2719056f0.md" }, { "id": "hm-fe6619d7ff5a38054385", "model_label": "Oasst-33B", "lab": "LAION / OpenAssistant", "source": "alce", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fe6619d7ff5a38054385.json", "report": "/leaderboard/reports/hm-fe6619d7ff5a38054385.md", "plan": "/leaderboard/plans/hm-fe6619d7ff5a38054385.md" }, { "id": "hm-fe8a78cb3a97d0126322", "model_label": "grok-4.20-0309-reasoning", "lab": "xAI", "source": "epoch_simpleqa_verified", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fe8a78cb3a97d0126322.json", "report": "/leaderboard/reports/hm-fe8a78cb3a97d0126322.md", "plan": "/leaderboard/plans/hm-fe8a78cb3a97d0126322.md" }, { "id": "hm-fe91c8715ffeb88568f0", "model_label": "mistralai/mistral-large-2411", "lab": "Mistral AI", "source": "vectara", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-fe91c8715ffeb88568f0.json", "report": "/leaderboard/reports/hm-fe91c8715ffeb88568f0.md", "plan": "/leaderboard/plans/hm-fe91c8715ffeb88568f0.md" }, { "id": "hm-ff0866fdf0b3066e8e79", "model_label": "qwen25-7b-instruct", "lab": "Alibaba", "source": "mask", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ff0866fdf0b3066e8e79.json", "report": "/leaderboard/reports/hm-ff0866fdf0b3066e8e79.md", "plan": "/leaderboard/plans/hm-ff0866fdf0b3066e8e79.md" }, { "id": "hm-ffd9641b7adce1ee226f", "model_label": "Claude Haiku 4.5", "lab": "Anthropic", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ffd9641b7adce1ee226f.json", "report": "/leaderboard/reports/hm-ffd9641b7adce1ee226f.md", "plan": "/leaderboard/plans/hm-ffd9641b7adce1ee226f.md" }, { "id": "hm-ffdb2e5490769c53c5b5", "model_label": "Gemini 2.5 Pro", "lab": "Google", "source": "bloom", "mark_status": "not_awarded", "scope": "Native source/configuration results only. This profile is not an awarded Honesty Mark.", "profile": "/leaderboard/profiles/hm-ffdb2e5490769c53c5b5.json", "report": "/leaderboard/reports/hm-ffdb2e5490769c53c5b5.md", "plan": "/leaderboard/plans/hm-ffdb2e5490769c53c5b5.md" } ] }