Skip to content
Back to articles
Models10 min

Measuring DeepSeek's Japanese: JMMLU, JCommonSenseQA, AI-Oh Benchmarks

Misaki HayashiAI Research Analyst
2026-04-2010 min
DeepSeekJapanese NLPBenchmarksJMMLUEvaluation

This article is published in Japanese. Summary in English below:

Measuring DeepSeek's Japanese: JMMLU, JCommonSenseQA, AI-Oh BenchmarksInternal benchmark of DeepSeek V3.2/R1 vs Qwen2.5-72B, Claude 3.5 Sonnet and GPT-4o-mini on JMMLU, JCommonSenseQA and AI-Oh, with reproducible prompt formats and conditions.

Start with a Free Consultation

Tell us about your IT challenges. We will propose the optimal solution for you.

Contact Us