Open Japanese LLM - Jnli Exact Match: leaderboard
The "Jnli 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 | llm-jp-3.1-13B-instruct4 | 94.33 | #835 |
| 2 | llm-jp-3.1-1.8B-instruct4 | 90.92 | #1273 |
| 3 | Awqward2.5-32B-Instruct | 89.93 | #372 |
| 4 | qwen2.5-bakeneko-32B-instruct-v2 | 89.77 | #562 |
| 5 | Rombos-LLM-V2.5-Qwen-32B | 89.77 | #366 |
| 6 | Qwen 2.5 32B Instruct | 89.73 | #499 |
| 7 | oxyge1-33B | 89.69 | #691 |
| 8 | Qwen2.5-32B-Instruct-CFT | 89.69 | #375 |
| 9 | QwQ 32B-Preview | 89.65 | #650 |
| 10 | ABEJA-Qwen2.5-32B-Japanese-v1.0 | 89.52 | #504 |
| 11 | Qwen2.5-32B-Instruct-abliterated-v2 | 89.48 | #394 |
| 12 | Qwentile2.5-32B-Instruct | 89.48 | #339 |
| 13 | Qwen 2.5 32B | 88.66 | #545 |
| 14 | cogito-v1-preview-qwen-14B | 88.37 | |
| 15 | EZO-Qwen2.5-32B-Instruct | 86.73 | #472 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=open-japanese-llm-jnli-exact-match · How It Works · Data refreshed daily, snapshot 2026-10-21.