Open Japanese LLM Leaderboard — leaderboard
Japanese language evaluation across 43 tasks including JCommonsenseQA, JMMLU, JSQuAD, MAWPS, and multilingual benchmarks.
Metric: Average Score (%). Source: huggingface.co. Status: saturation imminent. 418 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | QwQ 32B-Preview | 67.15 |
| 2 | Awqward2.5-32B-Instruct | 66.65 |
| 3 | Llama 3.1 70B Instruct | 66.38 |
| 4 | Llama 3.1 Nemotron 70B Instruct | 66.24 |
| 5 | Qwen2.5-32B-Instruct-abliterated-v2 | 65.61 |
| 6 | Qwen 2.5 32B Instruct | 65.53 |
| 7 | Qwen2.5-32B-Instruct-CFT | 65.51 |
| 8 | Saka-14B | 65.17 |
| 9 | tempmotacilla-cinerea-0308 | 64.65 |
| 10 | Qwentile2.5-32B-Instruct | 64.57 |
| 11 | Qwen2.5-14B-Instruct-1M | 64.53 |
| 12 | Qwen 2.5 14B | 64 |
| 13 | oxyge1-33B | 63.14 |
| 14 | Qwen 2.5 14B Instruct | 62.85 |
| 15 | Llama 3 70B | 62.73 |
Interactive version: theaggregate.ai/benchmark?slug=open-japanese-llm-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.