Medmarks - MedConceptsQA Medium — leaderboard
Metric: Score (%). Source: medmarks.ai. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4 | 99.82 |
| 2 | Gemini 3 Pro (Preview) | 99.02 |
| 3 | Claude Sonnet 4.5 | 97.35 |
| 4 | GPT-5.1 (Medium) | 97.07 |
| 5 | GPT-5.2 (Medium) | 95.93 |
| 6 | GLM-4.7 FP8 | 93.17 |
| 7 | Qwen 3 235B A22B (Thinking) | 85.95 |
| 8 | MiniMax-M2 | 84.02 |
| 9 | MiniMax-M2.1 | 83.83 |
| 10 | Llama 3.3 70B Instruct | 76.17 |
| 11 | Qwen 3 Next 80B A3B (Thinking) | 75.6 |
| 12 | GLM 4.5 Air | 75.38 |
| 13 | INTELLECT-3 | 74.1 |
| 14 | GPT-OSS-120B (High) | 73.8 |
| 15 | Qwen 3 Next 80B A3B Instruct | 72.62 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-medconceptsqa-medium · How the rankings work · Data refreshed daily, snapshot 2026-07-22.