ReLE - Medicine - Physician Exams: leaderboard
ReLE Chinese LLM benchmark (NoneLinear, formerly CLiB), a continuously updated Chinese-language evaluation run through each model's API. Medicine sub-dimension: Chinese physician qualification and attending-physician exam questions across specialties. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: nonelinear.com. Saturation forecast: Around February 2027. 147 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3.1 Pro | 92.3 | #17 |
| 2 | Claude Opus 5.5 | 91.7 | #3 |
| 3 | GLM-5.3 | 91 | #44 |
| 4 | Kimi K3 | 90.5 | #35 |
| 5 | Seed 2.0 Pro | 89.8 | #122 |
| 6 | GPT-5.6 Pro Sol | 89.2 | #21 |
| 7 | Kimi K2.7 Code | 89.1 | #95 |
| 8 | Claude Opus 5 | 89 | #16 |
| 9 | Grok 4.6 | 88.5 | #29 |
| 10 | Gemini 4 Argon | 88.3 | #9 |
| 11 | Kimi K2.6 | 88.2 | #113 |
| 12 | Gemini 3.1 Pro (Preview) | 87.9 | #64 |
| 13 | DeepSeek V4 Pro | 87.9 | #112 |
| 14 | Step 5 Preview | 87.8 | #53 |
| 15 | Qwen 3.7 Max | 87.6 | #85 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=rele-medicine-physician-exams · How It Works · Data refreshed daily, snapshot 2026-11-05.