MMRareBench - Diagnosis: leaderboard
MMRareBench (2026) diagnosis track: from a de-identified rare-disease case narrative with diagnosis mentions masked and several medical images, the model names the primary diagnosis. Rubric score (0-100) from a strict Qwen3-VL-235B judge; higher is better.
Metric: Diagnosis track (T1) score: open-ended primary diagnosis from a masked rare-disease case narrative and its medical images, graded 0-100 by a Qwen3-VL-235B judge with a strict track-specific rubric that awards credit only when a criterion is fully met (exact match weighted three times disease category and specificity, capped at 20 without an exact match); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 23 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 76.6 | #152 |
| 2 | GPT-5 | 75.9 | #178 |
| 3 | Gemini 2.5 Pro | 74 | #276 |
| 4 | Claude Sonnet 4.5 | 68.5 | #261 |
| 5 | GPT-4o | 62.5 | #751 |
| 6 | Gemini 2.5 Flash | 62.2 | #463 |
| 7 | Qwen 3 VL 235B A22B Instruct | 58.1 | #532 |
| 8 | Qwen 2.5 VL 72B Instruct | 52.6 | #841 |
| 9 | Hulu-Med-14B | 52 | #1607 |
| 10 | Lingshu-32B | 49.8 | #1113 |
| 11 | Qwen 3 VL 30B A3B Instruct | 46.9 | #895 |
| 12 | Qwen 2.5 VL 32B Instruct | 46.9 | #1062 |
| 13 | MedGemma-27B-IT | 43.7 | #1350 |
| 14 | HuluMed-7B | 42.2 | #2049 |
| 15 | Hulu-Med-4B | 39.8 | #2392 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mmrarebench-diagnosis · How It Works · Data refreshed daily, snapshot 2026-11-21.