Open Japanese LLM - MMLU EN Exact Match: leaderboard
The "MMLU EN Exact Match" subtask of Open Japanese LLM. A task from the Open Japanese LLM Leaderboard, evaluating models on Japanese-language knowledge, reasoning and understanding.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 418 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | cogito-v1-preview-qwen-14B | 82.65 | |
| 2 | Llama 3.3 70B Instruct | 81.62 | #534 |
| 3 | Llama 3.1 Nemotron 70B Instruct | 81.23 | #553 |
| 4 | Llama 3.1 70B Instruct | 80.99 | #561 |
| 5 | Qwentile2.5-32B-Instruct | 80.89 | #339 |
| 6 | Awqward2.5-32B-Instruct | 80.12 | #372 |
| 7 | oxyge1-33B | 80.07 | #691 |
| 8 | Rombos-LLM-V2.5-Qwen-32B | 80.03 | #366 |
| 9 | Qwen2.5-32B-Instruct-CFT | 80.01 | #375 |
| 10 | Qwen 2.5 32B Instruct | 80 | #499 |
| 11 | ABEJA-Qwen2.5-32B-Japanese-v1.0 | 79.94 | #504 |
| 12 | Qwen2.5-32B-Instruct-abliterated-v2 | 79.62 | #394 |
| 13 | QwQ 32B-Preview | 79.55 | #650 |
| 14 | EZO-Qwen2.5-32B-Instruct | 79.23 | #472 |
| 15 | Qwen 2.5 32B | 79.2 | #545 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=open-japanese-llm-mmlu-en-exact-match · How It Works · Data refreshed daily, snapshot 2026-10-21.