ClinicalMC (Chinese): leaderboard
ClinicalMC (Hou et al., 2026) on 1,275 Chinese multi-course electronic health records from MedEureka: acting as the doctor in a simulated hospital with GPT-4o-mini patient and examiner agents, the model triages, orders examinations, diagnoses and plans treatment at admission, then assesses and treats each later course and gives the discharge diagnosis. The score is the mean of eleven task scores in percent (accuracy, recall, F1, IoU and LLM-judged reasoning quality), higher is better.
Metric: Mean of 11 task scores (%; triage accuracy, examination recall, diagnosis F1, LLM-judged diagnosis basis and differential diagnosis, treatment and per-course IoU; GPT-4o-mini patient and examiner agents, gold inputs from earlier stages, mean of three runs; 1,275 Chinese records from MedEureka). Source: arxiv.org. Saturation forecast: Around August 2027. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 Next 80B A3B Instruct | 48.17 | #763 |
| 2 | GPT-5 Mini | 42.04 | #349 |
| 3 | Qwen Turbo | 38.62 | #2002 |
| 4 | Qwen 2.5 32B Instruct | 38.36 | #1216 |
| 5 | Qwen 2.5 7B Instruct | 38.27 | #2583 |
| 6 | Llama 3.3 70B Instruct | 37.93 | #1353 |
| 7 | Qwen 2.5 14B Instruct | 37.81 | #1745 |
| 8 | Qwen 2.5 72B Instruct | 37.59 | #1093 |
| 9 | GPT-4o Mini | 34.84 | #1627 |
| 10 | Mixtral 8x22B Instruct | 30.25 | #2052 |
| 11 | Llama 3.2 3B Instruct | 22.01 | #7185 |
| 12 | Falcon3-7B-Instruct | 21.33 | #6543 |
| 13 | Mistral 7B Instruct (v0.3) | 20.65 | #6698 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=clinicalmc-chinese · How It Works · Data refreshed daily, snapshot 2026-11-12.