Evals for Every Language - Japanese (ja): leaderboard
Average score across evaluation tasks in Japanese (ja), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 69 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.57 | #58 |
| 2 | Grok 4.20 | 77.18 | #175 |
| 3 | Claude Opus 4.7 | 76.57 | #49 |
| 4 | Gemini 3.1 Flash Lite | 76.07 | #191 |
| 5 | Claude Sonnet 4.6 | 75.95 | #90 |
| 6 | Claude Sonnet 4.5 | 75.82 | #142 |
| 7 | Kimi K2 | 75.73 | #243 |
| 8 | Gemini 2.5 Pro | 75.52 | #152 |
| 9 | GPT-5 | 75.37 | #98 |
| 10 | Claude Sonnet 4 | 75.1 | #199 |
| 11 | GPT-5.2 | 74.93 | #110 |
| 12 | GPT-4o | 74.75 | #343 |
| 13 | Llama 4 Maverick | 74.66 | #464 |
| 14 | DeepSeek V3.1 | 73.84 | #264 |
| 15 | Nova Pro (v1) | 73.8 | #497 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ja · How It Works · Data refreshed daily, snapshot 2026-10-20.