MMRareBench - Diagnosis F1: leaderboard
MMRareBench (2026) diagnosis track scored deterministically: token-level F1 (%) between the predicted primary diagnosis and the gold diagnosis or its aliases, from masked rare-disease case narratives with multiple medical images; higher is better.
Metric: Diagnosis track (T1) token-level F1 (%, SQuAD-style normalization, maximum over the gold diagnosis aliases) of the predicted primary diagnosis from a masked rare-disease case narrative and its medical images; 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) | 84.7 | #156 |
| 2 | Gemini 2.5 Pro | 80.1 | #280 |
| 3 | GPT-5 | 76.1 | #185 |
| 4 | Claude Sonnet 4.5 | 70.8 | #267 |
| 5 | GPT-4o | 70 | #754 |
| 6 | Gemini 2.5 Flash | 70 | #466 |
| 7 | Qwen 3 VL 235B A22B Instruct | 67.3 | #541 |
| 8 | Qwen 2.5 VL 72B Instruct | 61 | #849 |
| 9 | Hulu-Med-14B | 58.2 | #1621 |
| 10 | Qwen 3 VL 30B A3B Instruct | 56.3 | #903 |
| 11 | Lingshu-32B | 53.3 | #1125 |
| 12 | Claude Haiku 4.5 | 51.8 | #587 |
| 13 | MedGemma-27B-IT | 51.3 | #1359 |
| 14 | Qwen 2.5 VL 32B Instruct | 49.6 | #1065 |
| 15 | HuluMed-7B | 49 | #2061 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mmrarebench-diagnosis-f1 · How It Works · Data refreshed daily, snapshot 2026-11-22.