Medmarks - LongHealth Task 2 — leaderboard
Metric: Score (%). Source: medmarks.ai. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 90.96 |
| 2 | Claude Sonnet 4.5 | 90.58 |
| 3 | Qwen 3 Next 80B A3B Instruct | 90.33 |
| 4 | GPT-5.1 (Medium) | 90.33 |
| 5 | Qwen 3 235B A22B (Thinking) | 90.25 |
| 6 | Ministral-3-8B-Instruct-2512 | 89.29 |
| 7 | Magistral Small | 88.96 |
| 8 | Ministral-3-14B-Instruct-2512 | 88.88 |
| 9 | GLM-4.7 FP8 | 88.75 |
| 10 | GPT-5.2 (Medium) | 88.71 |
| 11 | Llama 3.3 70B Instruct | 88.62 |
| 12 | Qwen 2.5 32B Instruct | 88.46 |
| 13 | INTELLECT-3 | 88.46 |
| 14 | GPT-OSS-120B (High) | 88.38 |
| 15 | MiniMax-M2.1 | 88.17 |
Interactive version: theaggregate.ai/benchmark?slug=medmarks-longhealth-task-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.