JMed48k (Text-Only) - Midwife: leaderboard
Accuracy (%) on the text-only questions of the Japanese Midwife national licensing examination, 2020-2024, in JMed48k (2026), scored against the official answers of the Ministry of Health, Labour and Welfare; higher is better.
Metric: Accuracy (%) on the text-only scored items of the Japanese Midwife national licensing examination (2020-2024) in JMed48k-Eval, 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 | 94.3 | #276 | |
| 2 | GPT-5 | 90.4 | #178 | |
| 3 | Claude Sonnet 4 | 86.8 | #410 | |
| 4 | GPT-5 Mini | 84.4 | #364 | |
| 5 | Gemini 2.5 Flash | Non-reasoning | 84.4 | #463 |
| 6 | Qwen 3.5 397B A17B | Non-reasoning | 81.1 | #264 |
| 7 | Gemma 4 31B (IT) | 80.3 | #350 | |
| 8 | DeepSeek R1 | 79.5 | #482 | |
| 9 | Qwen 3.5 27B | Non-reasoning | 78.7 | #375 |
| 10 | Grok 4.20 | 78.3 | #301 | |
| 11 | Llama 4 Maverick | 72.4 | #1110 | |
| 12 | GLM-4.6V-Flash | Non-reasoning | 68.5 | #1040 |
| 13 | Qwen 3.5 9B | Non-reasoning | 66.5 | #828 |
| 14 | MedGemma-27B-IT | 61.8 | #1350 | |
| 15 | Lingshu-32B | 59.6 | #1113 |
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-midwife · How It Works · Data refreshed daily, snapshot 2026-11-21.