Medmarks - MTSamples Procedures — leaderboard
Metric: Score (%). Source: medmarks.ai. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Medium) | 88.74 |
| 2 | GPT-5.1 (Medium) | 86.61 |
| 3 | GPT-OSS-120B (High) | 86.48 |
| 4 | Qwen 3 235B A22B (Thinking) | 83.14 |
| 5 | Gemini 3 Pro (Preview) | 80.22 |
| 6 | GLM-4.7 FP8 | 78.56 |
| 7 | Claude Sonnet 4.5 | 77.35 |
| 8 | Qwen 3 30B A3B (Thinking) | 77.29 |
| 9 | GPT-OSS-20B (High) | 75.6 |
| 10 | Qwen 3 8B (Thinking) | 69.18 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-mtsamples-procedures · How the rankings work · Data refreshed daily, snapshot 2026-07-22.