JMed48k Benchmark

What is JMed48k?

JMed48k evaluates vision-language models on 48,862 Japanese medical licensing exam questions from 11 national examinations (2005-2025), with images annotated…

Released

2026-05-21

Evaluates

Biology & Drug Discovery, Multimodal

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.22080

JMed48k paper

• Paper https://arxiv.org/abs/2605.22080

Which sources cite JMed48k?

• JMed48k

Related Biology & Drug Discovery, Multimodal benchmarks

• 3DCodeBench
• A Large-Scale Dataset and Benchmark
• A-Bench
• A-OKVQA
• ABC-Bench
• ActionAtlas
• ActiveFly-Bench
• Agent Planning Benchmark