JMed48k (Text-Only) - Dentist: leaderboard

Accuracy (%) on the text-only questions of the Japanese Dentist national licensing examination, 2021-2025, 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 Dentist national licensing examination (2021-2025) 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

#ModelSettingScoreOverall rank
1GPT-592.9#178
2Gemini 2.5 Pro92.2#276
3GPT-5 Mini87.2#364
4Claude Sonnet 483.6#410
5Gemini 2.5 FlashNon-reasoning81.5#463
6Qwen 3.5 397B A17BNon-reasoning81.2#264
7Grok 4.2077#301
8Gemma 4 31B (IT)76.3#350
9Qwen 3.5 27BNon-reasoning76#375
10DeepSeek R175.6#482
11Llama 4 Maverick73.7#1110
12GLM-4.6V-FlashNon-reasoning72.4#1040
13Qwen 3.5 9BNon-reasoning60.3#828
14Lingshu-32B57.3#1113
15Hulu-Med-32B56.4#1221

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-dentist · How It Works · Data refreshed daily, snapshot 2026-11-21.