Open Japanese LLM - RC: leaderboard
The "RC" 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 | llm-jp-3.1-13B-instruct4 | 94.48 | #835 |
| 2 | Llama-3.1-Tulu-3-70B | 92.58 | #482 |
| 3 | llm-jp-3.1-1.8B-instruct4 | 92.57 | #1273 |
| 4 | Qwen 2.5 32B | 92.54 | #546 |
| 5 | QwQ 32B-Preview | 92.54 | #651 |
| 6 | Llama 3.1 70B | 92.29 | #592 |
| 7 | Llama 3.1 70B Instruct | 92.15 | #561 |
| 8 | Qwen 2.5 14B | 92.13 | #725 |
| 9 | Qwentile2.5-32B-Instruct | 92.13 | #339 |
| 10 | Llama 3 70B | 92.12 | #631 |
| 11 | Llama 3.1 Nemotron 70B Instruct | 92.02 | #554 |
| 12 | aya-23-35B | 91.75 | #883 |
| 13 | Llama 3 70B Instruct | 91.67 | #634 |
| 14 | tempmotacilla-cinerea-0308 | 91.46 | #395 |
| 15 | Qwen 2 57B A14B | 91.42 | #783 |
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-rc · How It Works · Data refreshed daily, snapshot 2026-10-20.