JMed48k (Text-Only): leaderboard
JMed48k (2026) is built from the official question booklets of 11 Japanese national healthcare licensing examinations. This board is accuracy (%) on the 9,905 text-only scored questions of the 2021-2025 exams, the unweighted mean over the 11 professions; higher is better.
Metric: Accuracy (%) on the 9,905 text-only scored JMed48k-Eval items (2021-2025 exams), 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: Estimated already saturated. 21 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 2.5 Pro | 95.5 | #276 | |
| 2 | GPT-5 | 95.1 | #178 | |
| 3 | GPT-5 Mini | 90.5 | #364 | |
| 4 | Claude Sonnet 4 | 89.3 | #410 | |
| 5 | Gemini 2.5 Flash | Non-reasoning | 86.6 | #463 |
| 6 | Qwen 3.5 397B A17B | Non-reasoning | 86.5 | #264 |
| 7 | Gemma 4 31B (IT) | 84.4 | #350 | |
| 8 | DeepSeek R1 | 83.1 | #482 | |
| 9 | Grok 4.20 | 82.4 | #301 | |
| 10 | Qwen 3.5 27B | Non-reasoning | 82 | #375 |
| 11 | Llama 4 Maverick | 77.7 | #1110 | |
| 12 | GLM-4.6V-Flash | Non-reasoning | 77.1 | #1040 |
| 13 | Qwen 3.5 9B | Non-reasoning | 68.9 | #828 |
| 14 | Lingshu-32B | 65 | #1113 | |
| 15 | MedGemma-27B-IT | 60.6 | #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-text-only · How It Works · Data refreshed daily, snapshot 2026-11-21.