Medmarks - Medbullets OP4 — leaderboard
Metric: Score (%). Source: medmarks.ai. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 90.91 |
| 2 | GPT-5.2 (Medium) | 90.04 |
| 3 | GPT-5.1 (Medium) | 89.5 |
| 4 | GLM-4.7 FP8 | 87.99 |
| 5 | Grok 4 | 87.77 |
| 6 | Qwen 3 235B A22B (Thinking) | 85.71 |
| 7 | GPT-OSS-120B (High) | 85.39 |
| 8 | GPT-OSS-120B (Medium) | 84.31 |
| 9 | Claude Sonnet 4.5 | 83.98 |
| 10 | MiniMax-M2.1 | 83.87 |
| 11 | Qwen 3 Next 80B A3B (Thinking) | 82.36 |
| 12 | GPT-OSS-120B (Low) | 81.6 |
| 13 | MiniMax-M2 | 81.39 |
| 14 | INTELLECT-3 | 80.63 |
| 15 | Qwen 3 Next 80B A3B Instruct | 80.19 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-medbullets-op4 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.