{"alignment_dimensions_with_observations":[],"alignment_dimensions_without_observations":["authorized_goal_following","constraint_compliance","non_deception","oversight_and_correction","robustness"],"configuration":{"benchmark":"SimpleQA","evaluation_date":null,"judge":"Source SimpleQA classifier; exact per-row grader identity not supplied by result table","model_revision":"gpt-4.1-2025-04-14","prompt_label":"assistant","reasoning_setting":null,"reported_period":"Historical table deprecated July 2025","source_commit":"652c89d0ca9df547706735883097e9537d40dc47","source_model_label":"gpt-4.1-2025-04-14"},"content_sha256":"d3334296deed7fff3fa298bb0855f91acd2f10ae7830fca5a4b469fc68cf15ee","coverage_meaning":"At least one observation, not complete or validated dimension coverage.","evidence_status":"recorded","honesty_dimensions_with_observations":["factual_accuracy"],"honesty_dimensions_without_observations":["belief_revision","citation_integrity","evidence_support","pressure_resistance","uncertainty"],"id":"hm-c77cccdc648b34618637","integrity_meaning":"Content-addressed record only; not an authenticated issuer signature or independent scientific validation.","lab":"OpenAI","limitations":["Historical OpenAI-reported results, not an independent Honesty.tools rerun. Prompt labels form separate cohorts. Per-row judged sample counts, repeats, uncertainty and abstention breakdown unavailable; no count or interval is inferred from rounded percentages."],"mark_status":"not_awarded","model_label":"gpt-4.1-2025-04-14","observations":[{"aggregation_blocker":"Historical OpenAI-reported results, not an independent Honesty.tools rerun. Prompt labels form separate cohorts. Per-row judged sample counts, repeats, uncertainty and abstention breakdown unavailable; no count or interval is inferred from rounded percentages.","attribution":"OpenAI simple-evals; Copyright (c) 2024 OpenAI","cohort":"simpleqa:652c89d0ca9df547706735883097e9537d40dc47:provider-reported:assistant","confidence_interval":null,"configuration":{"benchmark":"SimpleQA","evaluation_date":null,"judge":"Source SimpleQA classifier; exact per-row grader identity not supplied by result table","model_revision":"gpt-4.1-2025-04-14","prompt_label":"assistant","reasoning_setting":null,"reported_period":"Historical table deprecated July 2025","source_commit":"652c89d0ca9df547706735883097e9537d40dc47","source_model_label":"gpt-4.1-2025-04-14"},"configuration_id":"simpleqa:652c89d0ca9df547706735883097e9537d40dc47:provider-reported:assistant:gpt-4.1-2025-04-14","definition":"Source-reported percentage graded correct on SimpleQA. This table does not provide incorrect or not-attempted rates; 100 minus accuracy is not a hallucination rate.","denominator":null,"direction":"higher","evaluation_date":null,"evidence_class":"model_provider_reported","lab":"OpenAI","license":"MIT","license_url":"https://github.com/openai/simple-evals/blob/652c89d0ca9df547706735883097e9537d40dc47/LICENSE","metric":"simpleqa_correct","metric_label":"SimpleQA correct answers","model_label":"gpt-4.1-2025-04-14","numerator":null,"overall_score":null,"pillar":"factual_accuracy","profile_id":"hm-c77cccdc648b34618637","publication_eligible":true,"rank":2,"rank_meaning":"Descriptive native-metric order; not a significance or overall honesty rank.","source":"simpleqa","source_sha256":"d9647c4a0e34cd9b2b528ff6986141734aac6f5f2f18a068eeadb2af0b29786f","source_url":"https://github.com/openai/simple-evals/blob/652c89d0ca9df547706735883097e9537d40dc47/README.md#benchmark-results","split":"SimpleQA source evaluation","track":"honesty_evidence","uncertainty_note":"No inferential interval reconstructed from aggregate source values.","unit":"percent","value":41.6}],"overall_alignment_score":null,"overall_honesty_score":null,"priority_gaps":["belief_revision","citation_integrity","evidence_support","pressure_resistance","uncertainty"],"requirements":[{"detail":"The standard is a draft; no pass thresholds or award authority have been validated.","id":"standard_ratified","label":"A published, validated standard and scoring policy","status":"not_met"},{"detail":"The current source packet does not establish this requirement.","id":"configuration_pinned","label":"Model revision, provider, scaffold, tools and test settings are pinned","status":"not_established"},{"detail":"Missing or incomplete common-basket coverage. Some observations cover: factual_accuracy.","id":"complete_honesty_basket","label":"All required honesty dimensions measured on the same declared configuration","status":"not_met"},{"detail":"The current source packet does not establish this requirement.","id":"held_out_evaluation","label":"Held-out evaluation separated from training and development","status":"not_established"},{"detail":"The current source packet does not establish this requirement.","id":"usefulness_and_evasion","label":"Useful answering, abstention and evasion measured together","status":"not_established"},{"detail":"The current source packet does not establish this requirement.","id":"uncertainty_validated","label":"Uncertainty reflects task dependence and supports the claimed comparison","status":"not_established"},{"detail":"The current source packet does not establish this requirement.","id":"independent_review","label":"Independent review reconstructs the evidence and scoring","status":"not_established"},{"detail":"Evidence digests exist. Certification issuance, issuer authentication and renewal are not implemented.","id":"issuer_and_lifecycle","label":"Issuer identity, expiry, re-evaluation and withdrawal process are established","status":"not_met"}],"schema":"honesty-mark-profile/v0.1","scope":"Native source/configuration results only. This profile is not an awarded Honesty Mark.","source":"simpleqa","sources":[{"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/"}],"standard_sha256":"0cec00d16bbb6e2a02a28e43e43394e3eb309523c2ed697913154c4a2e6e6f6c","standard_version":"honesty-mark-standard/v0.1"}