Open Japanese LLM - Jcommonsenseqa Exact Match — leaderboard

Metric: Score (%). Source: huggingface.co. 418 models tracked.

Top models

#ModelScore
1aya-expanse-32B96.25
2EZO-Qwen2.5-32B-Instruct96.25
3Qwentile2.5-32B-Instruct96.07
4Qwen 2.5 32B95.98
5Qwen 2.5 14B95.98
6Awqward2.5-32B-Instruct95.89
7Qwen 2.5 32B Instruct95.8
8oxyge1-33B95.8
9Qwen2.5-32B-Instruct-CFT95.8
10Qwen2.5-32B-Instruct-abliterated-v295.71
11Qwen2.5-14B-Instruct-1M95.71
12lambda-qwen2.5-14B-dpo-test95.44
13DeepSeek R1 Distill Qwen 32B95.26
14tempmotacilla-cinerea-030895.26
15Qwen 2.5 14B Instruct95.17

Interactive version: theaggregate.ai/benchmark?slug=open-japanese-llm-jcommonsenseqa-exact-match · How the rankings work · Data refreshed daily, snapshot 2026-07-22.