Open Japanese LLM - Mbpp Pylint Check: leaderboard
The "Mbpp Pylint Check" 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 | Llama-3.1-Tulu-3-70B | 99.2 | #482 |
| 2 | qwen2.5-bakeneko-32B-instruct-v2 | 99 | #562 |
| 3 | llm-jp-3-3.7B | 99 | #1435 |
| 4 | Lamarckvergence-14B | 99 | #545 |
| 5 | Saka-14B | 98.19 | #344 |
| 6 | Llama 3.1 70B Instruct | 97.19 | #561 |
| 7 | Qwen2.5-14B-Instruct-1M | 95.78 | #578 |
| 8 | llm-jp-3-13B | 95.78 | #1219 |
| 9 | QwQ 32B-Preview | 94.78 | #651 |
| 10 | Awqward2.5-32B-Instruct | 92.97 | #371 |
| 11 | Qwen2.5-32B-Instruct-abliterated-v2 | 92.57 | #394 |
| 12 | Linkbricks-Horizon-AI-Korean-Superb-22B | 92.57 | #708 |
| 13 | Qwen 2 57B A14B | 92.37 | #783 |
| 14 | tempmotacilla-cinerea-0308 | 91.57 | #395 |
| 15 | Qwen 2.5 3B | 90.76 | #1211 |
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-mbpp-pylint-check · How It Works · Data refreshed daily, snapshot 2026-10-20.