LiveMedBench: leaderboard
Live medical benchmark with time-stamped real-world cases and after-cutoff scoring for measuring medical model robustness over time.
Metric: Overall Score (%). Source: zhilingyan.github.io. Saturation forecast: Around August 2027. 38 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 39.23 | #110 |
| 2 | GPT-5.1 | 38.45 | #135 |
| 3 | GPT-5 | 28.58 | #98 |
| 4 | Grok 4.1 | 28.28 | #227 |
| 5 | GPT-OSS-120B | 25.03 | #341 |
| 6 | GLM-4.5 | 22.46 | #275 |
| 7 | Gemini 3 Flash | 21.67 | #99 |
| 8 | Gemini 3 Pro | 18.29 | #80 |
| 9 | GLM-4.6 | 17.59 | #252 |
| 10 | Claude 3.7 Sonnet | 16.99 | #249 |
| 11 | Gemini 2.5 Pro | 16.06 | #152 |
| 12 | Qwen 3 14B | 15.45 | #537 |
| 13 | GPT-4.1 | 13.79 | #248 |
| 14 | QwQ-32B | 13.5 | #421 |
| 15 | GLM-4.7 (Thinking) | 13.35 | #192 (GLM-4.7) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=livemedbench · How It Works · Data refreshed daily, snapshot 2026-10-20.