Medmarks - MedConceptsQA Easy — leaderboard
Metric: Score (%). Source: medmarks.ai. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 100 |
| 2 | GPT-5.1 (Medium) | 99.97 |
| 3 | Grok 4 | 99.95 |
| 4 | Claude Sonnet 4.5 | 99.9 |
| 5 | GLM-4.7 FP8 | 99.9 |
| 6 | GPT-5.2 (Medium) | 99.85 |
| 7 | Qwen 3 235B A22B (Thinking) | 99.47 |
| 8 | MiniMax-M2.1 | 98.98 |
| 9 | Qwen 3 Next 80B A3B (Thinking) | 98.88 |
| 10 | Llama 3.3 70B Instruct | 98.47 |
| 11 | MiniMax-M2 | 98.23 |
| 12 | INTELLECT-3 | 97.95 |
| 13 | Qwen 3 Next 80B A3B Instruct | 97.8 |
| 14 | GPT-OSS-120B (High) | 97.57 |
| 15 | GPT-OSS-120B (Medium) | 96.08 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-medconceptsqa-easy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.