MMGist - Medical: leaderboard
Metric: Accuracy (%) on the Medical dimension (items kept from SLAKE and MedXpertQA); MMGist: 7,262 curated items from 18 vision-language benchmarks after removing items answerable without the image, items nearly every model solves and items with faulty labels; eight samples per item at temperature 1.0, step-by-step answer in a boxed block, 16,384 output tokens, medium effort where configurable; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (Medium) | 58 |
| 2 | Qwen 3.6 Plus | 50 |
| 3 | GPT-5 (Medium) | 46.6 |
| 4 | Qwen 3.6 35B A3B | 43 |
| 5 | Seed 2.0 Pro | 43 |
| 6 | Gemini 3.1 Flash Lite (Medium) | 41.8 |
| 7 | Seed 2.0 Lite | 39.6 |
| 8 | Gemma 4 31B | 39 |
| 9 | Claude Sonnet 4.6 (Medium) | 37.5 |
| 10 | GPT-5 Mini (Medium) | 37.2 |
| 11 | Gemma 4 26B A4B | 35.5 |
| 12 | Seed 2.0 Mini | 35.2 |
| 13 | Qwen 3.5 9B | 35 |
| 14 | Qwen 3.5 27B | 33.2 |
| 15 | Qwen 3.5 4B | 32.1 |
Interactive version: theaggregate.ai/benchmark?slug=mmgist-medical · How It Works · Data refreshed daily, snapshot 2026-09-29.