Harmlessness human feedback win rate (Anthropic)
Raters probe models in adversarial chats and pick the more harmless reply in head-to-head comparisons. Score is the win rate against a baseline model.
In-house Anthropic evaluation. A 50% win rate means equal to the baseline model, which changes between cards.
- Level
- Everyday Most adults, without training
- Scored
- Ranked by votes People pick the better of two answers, as in an arena, and the votes are turned into ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Claude 3 Sonnet leads with 87% among models released by Oct 2024
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 Oct 2024, 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 Claude 3 Sonnet 87%
- 2 Claude 3.5 Sonnet 52%
- 3 Claude 3.5 Sonnet (October 2024) 48%
- 4 Claude 3.5 Haiku 43%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude 3 Sonnet | 87% | Mar 2024 | Model card | |
| 2 | Claude 3.5 Sonnet | 52% | Jun 2024 | Model card | |
| 3 | Claude 3.5 Sonnet (October 2024) | 48% | Oct 2024 | Model card | |
| 4 | Claude 3.5 Haiku | 43% | Oct 2024 | Model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
The best score passed 85% in Mar 2024
All the scores we have, one dot each, so a model tested at several settings appears more than once.
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.
4 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 |
|---|---|---|---|---|
| 22 Oct 2024 | Claude 3.5 Sonnet (October 2024) model card | 48 | Human feedback win rate vs Claude 3.5 Sonnet baseline, Harmlessness (adversarial scenario) 48 (Figure 2) | Safety |
| 22 Oct 2024 | Claude 3.5 Haiku model card | 43 | Human feedback win rate vs Claude 3.5 Sonnet baseline, Harmlessness (adversarial scenario) 43 (Figure 2) | Safety |
| 20 Jun 2024 | Claude 3.5 Sonnet model card | 52 | Harmlessness, human preference win rate vs Claude 3 Opus baseline, adversarial scenarios (Figure 3) | Safety |
| 4 Mar 2024 | Claude 3 Sonnet model card | 87 | Human preference win rate vs Helpful-only baseline, Harmlessness (adversarial scenario) 87 (Figure 8) | 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%