JMed48k (Text-Only) - Occupational Therapist: leaderboard

Accuracy (%) on the text-only questions of the Japanese Occupational Therapist 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 Occupational Therapist 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-596#178
2Gemini 2.5 Pro95.2#276
3Claude Sonnet 491.7#410
4GPT-5 Mini91.5#364
5Gemini 2.5 FlashNon-reasoning88.8#463
6Qwen 3.5 397B A17BNon-reasoning88.7#264
7Gemma 4 31B (IT)86.5#350
8Grok 4.2085.6#301
9DeepSeek R185.3#482
10Qwen 3.5 27BNon-reasoning84.6#375
11Llama 4 Maverick80.4#1110
12GLM-4.6V-FlashNon-reasoning77.3#1040
13Qwen 3.5 9BNon-reasoning70.8#828
14Lingshu-32B67.6#1113
15MedGemma-27B-IT61.3#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-occupational-therapist · How It Works · Data refreshed daily, snapshot 2026-11-21.