ClinPivot: leaderboard
Clinical foundation models are evaluated with factual or exam-style medical QA, but treatment decisions must change when patient context changes. We introduce ClinPivot, an auditable treatment-decision benchmark built from biomedical relations and pivoted patient contexts. ClinPivot asks whether models change treatment choices when new clinical constraints shift the action space. We find that stro
Metric: ClinPivot (self-reported). Source: benchmarklist.com. Saturation forecast: Around April 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 | 69.32 | #183 |
| 2 | Claude Sonnet 4.5 | 67.57 | #142 |
| 3 | Qwen 3 235B A22B | 65.74 | #313 |
| 4 | Qwen 3.5 397B A17B | 64.22 | #146 |
| 5 | DeepSeek R1 | 63.1 | #251 |
| 6 | Llama 4 Maverick | 61.93 | #464 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=clinpivot · How It Works · Data refreshed daily, snapshot 2026-10-20.