Medmarks - Medbullets OP5 — leaderboard
Metric: Score (%). Source: medmarks.ai. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 87.66 |
| 2 | GPT-5.2 (Medium) | 87.23 |
| 3 | GPT-5.1 (Medium) | 87.23 |
| 4 | GLM-4.7 FP8 | 84.52 |
| 5 | Grok 4 | 83.98 |
| 6 | GPT-OSS-120B (High) | 82.58 |
| 7 | Qwen 3 235B A22B (Thinking) | 81.82 |
| 8 | GPT-OSS-120B (Medium) | 80.95 |
| 9 | Claude Sonnet 4.5 | 80.52 |
| 10 | Qwen 3 Next 80B A3B (Thinking) | 78.79 |
| 11 | MiniMax-M2.1 | 77.27 |
| 12 | Qwen 3 Next 80B A3B Instruct | 76.95 |
| 13 | INTELLECT-3 | 76.84 |
| 14 | MiniMax-M2 | 76.41 |
| 15 | GPT-OSS-120B (Low) | 76.08 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-medbullets-op5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.