MMGist - Medical: leaderboard
MMGist (2026) is a curated multimodal benchmark: 7,262 items kept from 18 vision-language benchmarks after dropping items that can be answered without the image, items nearly all models solve, and items with faulty labels. This board is accuracy in percent on the Medical items, drawn from SLAKE and MedXpertQA; higher is better.
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 February 2028. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (Medium) | 58 | #94 (Gemini 3.1 Pro (Preview)) |
| 2 | Qwen 3.6 Plus | 50 | #222 |
| 3 | GPT-5 (Medium) | 46.6 | #167 (GPT-5) |
| 4 | Qwen 3.6 35B A3B | 43 | #462 |
| 5 | Seed 2.0 Pro | 43 | #211 |
| 6 | Gemini 3.1 Flash Lite (Medium) | 41.8 | #364 (Gemini 3.1 Flash Lite) |
| 7 | Seed 2.0 Lite | 39.6 | #289 |
| 8 | Gemma 4 31B | 39 | #394 |
| 9 | Claude Sonnet 4.6 (Medium) | 37.5 | #161 (Claude Sonnet 4.6) |
| 10 | GPT-5 Mini (Medium) | 37.2 | #348 (GPT-5 Mini) |
| 11 | Gemma 4 26B A4B | 35.5 | #615 |
| 12 | Seed 2.0 Mini | 35.2 | #508 |
| 13 | Qwen 3.5 9B | 35 | #803 |
| 14 | Qwen 3.5 27B | 33.2 | #359 |
| 15 | Qwen 3.5 4B | 32.1 | #1175 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mmgist-medical · How It Works · Data refreshed daily, snapshot 2026-11-13.