MEDSYN (Chinese) - Differential Diagnosis Coverage: leaderboard
Metric: Differential-diagnosis coverage rate (%) on the 54 Chinese cases: share of cases whose generated differential list includes the final diagnosis, judged by GPT-5 on a 0-5 scale with a score of at least 4 counting, from the case's history, examination and raw-image clinical evidence; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 66.04 | #105 |
| 2 | Gemini 2.5 Pro | 64.81 | #145 |
| 3 | O3 | 64.81 | #121 |
| 4 | Claude Opus 4.5 | 61.11 | #79 |
| 5 | Gemini 2.5 Flash | 54.72 | #237 |
| 6 | Qwen 2.5 VL 72B Instruct | 51.85 | #364 |
| 7 | InternVL3-78B | 38.89 | #345 |
| 8 | Qwen 2.5 VL 7B Instruct | 22.22 | #643 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=medsyn-chinese-differential-diagnosis-coverage · How It Works · Data refreshed daily, snapshot 2026-10-11.