JMed48k (Text-Only) - Clinical Laboratory Technologist: leaderboard

Accuracy (%) on the text-only questions of the Japanese Clinical Laboratory Technologist 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 Clinical Laboratory Technologist 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-597.6#178
2Gemini 2.5 Pro96.9#276
3GPT-5 Mini94.1#364
4Claude Sonnet 492.2#410
5Gemini 2.5 FlashNon-reasoning91#463
6Qwen 3.5 397B A17BNon-reasoning90.6#264
7Gemma 4 31B (IT)87.1#350
8DeepSeek R186#482
9Grok 4.2085.5#301
10GLM-4.6V-FlashNon-reasoning85.2#1040
11Qwen 3.5 27BNon-reasoning84.7#375
12Llama 4 Maverick81.3#1110
13Qwen 3.5 9BNon-reasoning70.9#828
14Lingshu-32B65.7#1113
15MedGemma-27B-IT60.2#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-clinical-laboratory-technologist · How It Works · Data refreshed daily, snapshot 2026-11-21.