AcuityBench (Conversational): leaderboard
AcuityBench (2026) tests whether language models recommend the right urgency of care (four acuity levels) for user medical presentations; in this conversational format the model answers naturally and a GPT-4.1 judge infers the level it communicated. Exact-match accuracy in percent on 527 clear consensus cases; higher is better.
Metric: Exact acuity match (%) in the conversational format on the 527 clear consensus cases: the model answers naturally without being asked for a label, a GPT-4.1 judge infers the communicated acuity level, mode of five samples at temperature 1; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 78 | #463 |
| 2 | GPT-5.4 | 77.2 | #135 |
| 3 | DeepSeek V3.1 | 76.8 | #511 |
| 4 | Gemini 2.5 Pro | 76.7 | #276 |
| 5 | Claude Sonnet 4.6 | 74.4 | #173 |
| 6 | Claude Opus 4.7 | 71.9 | #85 |
| 7 | GPT-4.1 | 71.4 | #505 |
| 8 | Claude Haiku 4.5 (20251001) | 70 | #543 |
| 9 | GPT-5 Mini | 67.7 | #364 |
| 10 | Qwen 2.5 72B Instruct Turbo | 66.8 | #1213 |
| 11 | Qwen 2.5 7B Turbo Instruct | 65.1 | #2617 |
| 12 | Llama 3.3 70B Instruct | 61.9 | #1385 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=acuitybench-conversational · How It Works · Data refreshed daily, snapshot 2026-11-21.