Open Japanese LLM - Jemhopqa Char F1: leaderboard
The "Jemhopqa Char F1" 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 | ABEJA-Qwen2.5-32B-Japanese-v1.0 | 65.36 | #503 |
| 2 | Llama 3.3 70B Instruct | 65.28 | #534 |
| 3 | llm-jp-3.1-13B-instruct4 | 63.72 | #835 |
| 4 | Qwentile2.5-32B-Instruct | 63.68 | #339 |
| 5 | Llama-3.1-Tulu-3-70B | 63.66 | #482 |
| 6 | Llama 3.1 70B Instruct | 63.31 | #561 |
| 7 | Llama 3.1 Nemotron 70B Instruct | 62.05 | #554 |
| 8 | QwQ 32B-Preview | 61.71 | #651 |
| 9 | Llama-3.3-Swallow-70B-Instruct-v0.4 | 61.58 | #529 |
| 10 | Llama 3.1 70B | 61.45 | #592 |
| 11 | Llama 3 70B Instruct | 61.02 | #634 |
| 12 | Llama 3 70B | 60.56 | #631 |
| 13 | Saka-14B | 59.69 | #344 |
| 14 | Qwen 2.5 14B Instruct | 58.83 | #647 |
| 15 | aya-expanse-32B | 58.15 | #692 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-japanese-llm-jemhopqa-char-f1 · How It Works · Data refreshed daily, snapshot 2026-10-20.