JMed48k (With Images): leaderboard
JMed48k (2026) is built from the official question booklets of 11 Japanese national healthcare licensing examinations. This board is accuracy (%) of vision-language models on the 2,579 scored questions that come with images (clinical photographs, radiology, charts and others), the unweighted mean over the 11 professions; higher is better.
Metric: Accuracy (%) on the 2,579 scored JMed48k-Eval items that include images, unweighted macro average over the 11 professions, official MHLW gold answers, single-shot Japanese prompts at temperature 0 with reasoning disabled where the model has a switch, JSON-constrained answers; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 20 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 2.5 Pro | 79.7 | #276 | |
| 2 | GPT-5 | 78.8 | #178 | |
| 3 | GPT-5 Mini | 70.6 | #364 | |
| 4 | Gemini 2.5 Flash | Non-reasoning | 66.7 | #463 |
| 5 | Qwen 3.5 397B A17B | Non-reasoning | 63.6 | #264 |
| 6 | Gemma 4 31B (IT) | 61.6 | #350 | |
| 7 | Claude Sonnet 4 | 57.7 | #410 | |
| 8 | Qwen 3.5 27B | Non-reasoning | 57.6 | #375 |
| 9 | Llama 4 Maverick | 53.8 | #1110 | |
| 10 | Grok 4.20 | 53.6 | #301 | |
| 11 | GLM-4.6V-Flash | Non-reasoning | 52.8 | #1040 |
| 12 | Lingshu-32B | 45 | #1113 | |
| 13 | Qwen 3.5 9B | Non-reasoning | 41.8 | #828 |
| 14 | Hulu-Med-32B | 36.8 | #1221 | |
| 15 | MedGemma-27B-IT | 34.2 | #1350 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=jmed48k-with-images · How It Works · Data refreshed daily, snapshot 2026-11-21.