Open Japanese LLM - Jcommonsenseqa Exact Match: leaderboard
The "Jcommonsenseqa 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 | Llama-3.3-Swallow-70B-Instruct-v0.4 | 97.86 | #529 |
| 2 | ABEJA-Qwen2.5-32B-Japanese-v1.0 | 97.14 | #503 |
| 3 | llm-jp-3.1-13B-instruct4 | 97.05 | #835 |
| 4 | aya-expanse-32B | 96.25 | #692 |
| 5 | EZO-Qwen2.5-32B-Instruct | 96.25 | #471 |
| 6 | Qwentile2.5-32B-Instruct | 96.07 | #339 |
| 7 | cogito-v1-preview-qwen-14B | 95.98 | |
| 8 | Qwen 2.5 14B | 95.98 | #725 |
| 9 | Qwen 2.5 32B | 95.98 | #546 |
| 10 | Awqward2.5-32B-Instruct | 95.89 | #371 |
| 11 | Qwen 2.5 32B Instruct | 95.8 | #498 |
| 12 | oxyge1-33B | 95.8 | #690 |
| 13 | Qwen2.5-32B-Instruct-CFT | 95.8 | #375 |
| 14 | qwen2.5-bakeneko-32B-instruct-v2 | 95.8 | #562 |
| 15 | Rombos-LLM-V2.5-Qwen-32B | 95.8 | #367 |
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-jcommonsenseqa-exact-match · How It Works · Data refreshed daily, snapshot 2026-10-20.