Refusal to assist with AI safety R&D (Anthropic)
Models receive single-turn coding requests for legitimate AI safety research with user context. Score is the refusal rate, where lower is better.
In-house Anthropic evaluation. The tasks are not public.
- Made by
- Anthropic
- Released
- February 2026
- Kind
- Deception and alignment
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- Claude Fable 5 #11 on the capability index
- Last in a system card
- June 2026
- Last model added
- June 2026
Claude Fable 5 leads with 3.10% among models released by June 2026
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 June 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 15 more
- 1 Claude Fable 5 3.10%
- 2 Claude Opus 4.6 14%
- 3 Claude Mythos Preview 18.7%
- 4 Claude Opus 4.7 33.1%
- 5 Claude Sonnet 4.6 38%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 3.10% | Jun 2026 | Lab model card | |
| 2 | Claude Opus 4.6 | 14% | Feb 2026 | Lab model card | |
| 3 | Claude Mythos Preview | 18.7% | Apr 2026 | Lab model card | |
| 4 | Claude Opus 4.7 | 33.1% | Apr 2026 | Lab model card | |
| 5 | Claude Sonnet 4.6 | 38% | Feb 2026 | Lab model card |
2 models have held number one in labs’ own numbers since its release in February 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
6 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 |
|---|---|---|---|---|
| Jun 9, 2026 | Claude Fable 5 system card | 3.1 | Refusal to assist with AI safety R&D, safety-research refusal rate with extended thinking, 0.031 printed on chart, lower is better (Figure 6.3.4.A) | Alignment |
| May 28, 2026 | Claude Opus 4.8 system card | Refusal to assist with AI safety R&D, refusal rate with and without extended thinking, chart without printed values. Text says the lowest of recent models (6.3.4, Figure 6.3.4.A) | Alignment | |
| Apr 16, 2026 | Claude Opus 4.7 system card | 33.1 | Alignment-research refusals, refusal score 0.331 with thinking (16k budget), lower is better. 0.338 without thinking (6.3.4, Figure 6.3.4.A) | Alignment |
| Apr 7, 2026 | Claude Mythos Preview system card | 18.7 | Alignment Research Refusals Rate with thinking, 0.187 printed on chart (text says 18%), lower is better; 0.142 without thinking (4.3.4, Figure 4.3.4.A) | Alignment |
| Feb 17, 2026 | Claude Sonnet 4.6 system card | 38 | Alignment research refusals rate, thinking 0.380; no thinking 0.441 (Figure 4.6.1.A) | Alignment |
| Feb 5, 2026 | Claude Opus 4.6 system card | 14 | Refusal rate on reasonable AI safety research tasks, lower is better, stated in text (6.3.6, Figure 6.3.6.A) | Alignment |
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% - 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. Gemini 4 Carbon 0%
- DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%