Single-turn benign request evaluations (Anthropic)
Claude Fable 5.1 0% leads since Sep 2026 Only in system cards
Models answer benign requests on sensitive topics. Score is the refusal rate, where lower is better.
In-house Anthropic evaluation. The tasks are not public.
Made by Anthropic Released May 2025 Refusing harmful requests Tasks kept private Last in a system card Oct 2026
Last model added Oct 2026
- 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.
18
Models scored in lab cards
18
System cards report it, from 1 lab
Claude Fable 5.1 leads with 0%
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.
- 1 Claude Fable 5.1 0%
- 2 Claude Fable 5 0.01%
- 3 Claude Sonnet 4.5 0.02%
- 4 Claude Haiku 4.5 0.02%
- 5 Claude Sonnet 5.5 0.02%
- 6 Claude Opus 5.5 0.03%
- 7 Claude Mythos Preview 0.06%
- 8 Claude Opus 4 0.07%
- 9 Claude Opus 4.1 0.08%
- 10 Claude Opus 5 0.09%
- 11 Claude Haiku 5.5 0.17%
- 12 Claude Sonnet 4 0.23%
- 13 Claude Opus 4.5 0.23%
- 14 Claude Opus 4.7 0.28%
- 15 Claude Opus 4.8 0.36%
- 16 Claude Sonnet 4.6 0.41%
- 17 Claude Sonnet 5 0.59%
- 18 Claude Opus 4.6 0.68%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 0% | Sep 2026 | Model card | |
| 2 | Claude Fable 5 | 0.01% | Jun 2026 | Model card | |
| 3 | Claude Sonnet 4.5 | 0.02% | Sep 2025 | Model card | |
| 4 | Claude Haiku 4.5 | 0.02% | Oct 2025 | Model card | |
| 5 | Claude Sonnet 5.5 | 0.02% | Sep 2026 | Model card | |
| 6 | Claude Opus 5.5 | 0.03% | Sep 2026 | Model card | |
| 7 | Claude Mythos Preview | 0.06% | Apr 2026 | Model card | |
| 8 | Claude Opus 4 | 0.07% | May 2025 | Model card | |
| 9 | Claude Opus 4.1 | 0.08% | Aug 2025 | Model card | |
| 10 | Claude Opus 5 | 0.09% | Jul 2026 | Model card | |
| 11 | Claude Haiku 5.5 | 0.17% | Oct 2026 | Model card | |
| 12 | Claude Sonnet 4 | 0.23% | May 2025 | Model card | |
| 13 | Claude Opus 4.5 | 0.23% | Nov 2025 | Model card | |
| 14 | Claude Opus 4.7 | 0.28% | Apr 2026 | Model card | |
| 15 | Claude Opus 4.8 | 0.36% | May 2026 | Model card | |
| 16 | Claude Sonnet 4.6 | 0.41% | Feb 2026 | Model card | |
| 17 | Claude Sonnet 5 | 0.59% | Jun 2026 | Model card | |
| 18 | Claude Opus 4.6 | 0.68% | Feb 2026 | Model card |
4 models have held number one since its release in May 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Anthropic
Scores over time
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.
18 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 Oct 2026 | Claude Haiku 5.5 system card | 0.17 | Single-turn benign request evaluations, overall refusal rate, API without system prompt (claude.ai 0.82%) (Table 4.1.2.A) | Safety |
| 28 Sep 2026 | Claude Sonnet 5.5 system card | 0.02 | Single-turn benign requests, overall refusal rate, API without system prompt (claude.ai 0.20%), lower is better (Table 4.1.2.A) | Safety |
| 22 Sep 2026 | Claude Opus 5.5 system card | 0.03 | Single-turn benign requests, overall over-refusal rate, API without a system prompt, lower is better (claude.ai 0.38%) (Table 4.1.2.A) | Safety |
| 1 Sep 2026 | Claude Fable 5.1 system card | 0 | Single-turn benign request evaluations, overall refusal rate, API without a system prompt; claude.ai 0.34%, lower is better (Table 4.1.2.A) | Safety |
| 24 Jul 2026 | Claude Opus 5 system card | 0.09 | Single-turn benign requests, overall over-refusal rate, API without a system prompt, lower is better (claude.ai 0.47%) (Table 4.1.2.A) | Safety |
| 30 Jun 2026 | Claude Sonnet 5 system card | 0.59 | Single-turn benign requests, overall refusal rate, API without a system prompt, lower is better (claude.ai 1.54%) (Table 4.1.2.A) | Safety |
| 9 Jun 2026 | Claude Fable 5 system card | 0.01 | Single-turn benign request evaluations, overall refusal rate, API without a system prompt; claude.ai 0.49%, lower is better (Table 4.1.2.A) | Safety |
| 28 May 2026 | Claude Opus 4.8 system card | 0.36 | Single-turn benign requests, overall over-refusal rate, API without a system prompt, lower is better (claude.ai 0.49%) (Table 4.1.2.A) | Safety |
| 16 Apr 2026 | Claude Opus 4.7 system card | 0.28 | Single-turn benign request evaluations, overall refusal rate, lower is better. Without thinking 0.50, with adaptive thinking 0.06 (Table 4.1.2.A) | Safety |
| 7 Apr 2026 | Claude Mythos Preview system card | 0.06 | Single-turn benign request evaluations, overall refusal rate, lower is better (Table 8.1.1.2.A); 0.09 without thinking, 0.02 with thinking | Safety |
| 17 Feb 2026 | Claude Sonnet 4.6 system card | 0.41 | Single-turn benign request evaluations, overall refusal rate, lower is better (Table 3.1.2.A) | Safety |
| 5 Feb 2026 | Claude Opus 4.6 system card | 0.68 | Single-turn benign request evaluations, overall refusal rate, lower is better, 7 languages (Table 3.1.2.A); default 0.80, extended thinking 0.56 | Safety |
| 24 Nov 2025 | Claude Opus 4.5 system card | 0.23 | Single-turn benign request evaluations, overall refusal rate, lower is better, 6 languages (Table 3.1.2.A; default 0.18%, extended thinking 0.27%) | Safety |
| 15 Oct 2025 | Claude Haiku 4.5 system card | 0.02 | Single-turn benign request evaluations, overall refusal rate, lower is better (Table 2.1.2.A) | Safety |
| 29 Sep 2025 | Claude Sonnet 4.5 system card | 0.02 | Single-turn benign request evaluations, overall refusal rate 0.02% (± 0.04%), lower is better, run without safety classifiers. Standard thinking 0.05%, extended thinking 0.00% (Table 2.1.2.A) | Safety |
| 5 Aug 2025 | Claude Opus 4.1 system card addendum | 0.08 | Single-turn benign request evaluations, overall refusal rate 0.08% (± 0.09%), lower is better. Standard thinking 0.13%, extended thinking 0.04% (Table 2.1.B) | Safety |
| 22 May 2025 | Claude Sonnet 4 system card | 0.23 | Single-turn benign request evaluations, overall refusal rate 0.23% (± 0.11%), lower is better. Standard thinking 0.43%, extended thinking 0.03% (Table 2.2.A) | Safety |
| 22 May 2025 | Claude Opus 4 system card | 0.07 | Single-turn benign request evaluations, overall refusal rate 0.07% (± 0.07%), lower is better. Standard thinking 0.12%, extended thinking 0.02% (Table 2.2.A) | 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%