Nejumi 4

Japanese

Comprehensive Japanese LLM evaluation covering reasoning, knowledge, coding, safety.

Metrics
Score (0-1)
Dataset Eval Code

How to Run

Visit nejumi.ai for evaluation or use llm-jp-eval framework

Leaderboard

Rank Model Provider Parameters Score
1 GPT-5.2 OpenAI Unknown 82.8%
2 Gemini 3 Pro Google Unknown 81.3%
3 Claude Opus 4.5 Anthropic Unknown 80.6%
4 Grok 4.1 xAI Unknown 79.5%
5 Claude Sonnet 4.5 Anthropic Unknown 78.8%
6 DeepSeek-V3.2 DeepSeek 671B MoE 77.2%