Medmarks - MedCaseReasoning — leaderboard
Metric: Score (%). Source: medmarks.ai. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Medium) | 52.6 |
| 2 | GPT-5.1 (Medium) | 48.6 |
| 3 | Gemini 3 Pro (Preview) | 48 |
| 4 | GPT-OSS-120B (High) | 45.4 |
| 5 | Claude Sonnet 4.5 | 43 |
| 6 | GLM-4.7 FP8 | 42.6 |
| 7 | Qwen 3 235B A22B (Thinking) | 36.6 |
| 8 | GPT-OSS-20B (High) | 32.6 |
| 9 | Qwen 3 30B A3B (Thinking) | 29.4 |
| 10 | Qwen 3 8B (Thinking) | 21.4 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-medcasereasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.