JMed48k (Text-Only) - Orthoptist: leaderboard

Accuracy (%) on the text-only questions of the Japanese Orthoptist 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 Orthoptist 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-593.2#178
2Gemini 2.5 Pro92.2#276
3GPT-5 Mini86.3#364
4Claude Sonnet 477.3#410
5Qwen 3.5 397B A17BNon-reasoning76.5#264
6Gemini 2.5 FlashNon-reasoning74.2#463
7DeepSeek R173.8#482
8Qwen 3.5 27BNon-reasoning70.6#375
9Gemma 4 31B (IT)70#350
10GLM-4.6V-FlashNon-reasoning67.7#1040
11Grok 4.2067.6#301
12Llama 4 Maverick66.3#1110
13Qwen 3.5 9BNon-reasoning54.4#828
14Lingshu-32B51.5#1113
15MedGemma-27B-IT43.4#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-orthoptist · How It Works · Data refreshed daily, snapshot 2026-11-21.