Standard Refusal Evaluation
o1 100% leads since Dec 2024 Only in system cards
Models answer disallowed and benign safety-related prompts across policy categories. An autograder scores not_unsafe and not_overrefuse.
In-house OpenAI evaluation. Some cards give category scores only.
Made by OpenAI Released Aug 2024 Refusing harmful requests Tasks kept private Last in a system card Aug 2025
Last model added Aug 2025
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
8
Models scored in lab cards
17
System cards report it, from 1 lab
3 models share the top score of 100% among models released by Feb 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Feb 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 o1 100%
- 2 OpenAI Computer-Using Agent (CUA) 100%
- 3 o3-mini 100%
- 4 o1-preview 99.5%
- 5 o1-mini 99%
- 6 GPT-4.5 99%
- 7 OpenAI deep research 97%
- 8 GPT-4o May 2024 93%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1 | 100% | Dec 2024 | Model card | |
| 2 | OpenAI Computer-Using Agent (CUA) | 100% | Jan 2025 | Model card | |
| 3 | o3-mini | 100% | Jan 2025 | Model card | |
| 4 | o1-preview | 99.5% | Sep 2024 | Model card | |
| 5 | o1-mini | 99% | Sep 2024 | Model card | |
| 6 | GPT-4.5 | 99% | Feb 2025 | Model card | |
| 7 | OpenAI deep research | 97% | Feb 2025 | Model card | |
| 8 | GPT-4o May 2024 | 93% | Aug 2024 | Model card |
3 models have held number one since its release in Aug 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
OpenAI
The best score passed 85% in Aug 2024
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
Best so far
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
17 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 7 Aug 2025 | GPT-5 system card | Standard Disallowed Content Evaluation, not_unsafe, 8 categories, no overall score (Table 2) | Safety | |
| 7 Aug 2025 | GPT-5 nano system card | standard disallowed content evaluation, gpt-5-thinking-nano, 8 categories, no overall score (Table 23) | Safety | |
| 7 Aug 2025 | GPT-5 mini system card | standard disallowed content evaluation, gpt-5-thinking-mini, 8 categories, no overall score (Table 23) | Safety | |
| 5 Aug 2025 | gpt-oss-20b model card | Standard Disallowed Content Evaluation, not_unsafe, 8 categories, no overall score (Table 4) | Safety | |
| 5 Aug 2025 | gpt-oss-120b model card | Standard Disallowed Content Evaluation, not_unsafe, 8 categories, no overall score (Table 4) | Safety | |
| 17 Jul 2025 | ChatGPT agent system card | Standard Disallowed Content Evaluation, not_unsafe, 8 rows from 0.988 to 1.000, no overall score (Table 1) | Safety | |
| 16 May 2025 | codex-1 system card addendum | Standard refusal evaluation, not_unsafe, 13 categories from 0.96 to 1, no overall score (Table 1) | Safety | |
| 16 Apr 2025 | o4-mini system card | Standard refusal evaluation, not_unsafe in 13 categories with no aggregate, aggregate not_overrefuse only (Table 1) | Safety | |
| 16 Apr 2025 | o3 system card | Standard refusal evaluation, not_unsafe in 13 categories with no aggregate, aggregate not_overrefuse only (Table 1) | Safety | |
| 27 Feb 2025 | GPT-4.5 system card | 99 | Standard Refusal Evaluation, not_unsafe, not_overrefuse 0.71 (Table 1) | Safety |
| 25 Feb 2025 | OpenAI deep research system card | 97 | Disallowed content evaluations, not_unsafe 0.97, not_overrefuse 0.86 (Table 3) | Safety |
| 31 Jan 2025 | o3-mini system card | 100 | Standard Refusal Evaluation, not_unsafe, not_overrefuse 0.92 (Table 1) | Safety |
| 23 Jan 2025 | OpenAI Computer-Using Agent (CUA) system card | 100 | Standard refusal evaluation, not_unsafe 100%, not_overrefuse 55% (Table 3, categories in Table 4) | Safety |
| 5 Dec 2024 | o1 system card | 100 | Standard Refusal Evaluation, not_unsafe 1 (not_overrefuse 0.93) (Table 1) | Safety |
| 12 Sep 2024 | o1-preview system card | 99.5 | Standard Refusal Evaluation, not_unsafe (not_overrefuse 0.93) (Table 1) | Safety |
| 12 Sep 2024 | o1-mini system card | 99 | Standard Refusal Evaluation, not_unsafe (not_overrefuse 0.9) (Table 1) | Safety |
| 8 Aug 2024 | GPT-4o system card | 93 | Text safety evaluations converted to audio, Audio not_unsafe (Table 5, not_overrefuse 0.82); Appendix A Table 11 gives New GPT-4o Audio not_unsafe 1.0, not_overrefuse 0.91 | Safety |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%