Open Chinese LLM - WinoGrande: leaderboard
The "WinoGrande" subtask of Open Chinese LLM. A task from the Open Chinese LLM Leaderboard, evaluating models on Chinese-language knowledge, reasoning and understanding.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 339 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | luxia-21.4B-alignment-v1.0 | 74.35 | #965 |
| 2 | luxia-21.4B-alignment-v1.2 | 73.72 | #1012 |
| 3 | internlm2-20B | 72.69 | #943 |
| 4 | UNA-SimpleSmaug-34B-v1beta | 72.14 | #712 |
| 5 | Luminex-34B-v0.2 | 71.9 | #696 |
| 6 | Luminex-34B-v0.1 | 71.9 | #697 |
| 7 | Bagel-Hermes-34B-Slerp | 71.59 | #715 |
| 8 | Smaug-34B-v0.1 | 71.59 | #723 |
| 9 | free-evo-qwen72B-v0.8-re | 71.43 | #435 |
| 10 | Qwen 2 72B | 71.35 | #521 |
| 11 | Rhea-72B-v0.5 | 71.11 | #556 |
| 12 | YiSM-blossom5.1-34B-SLERP | 70.88 | #591 |
| 13 | Yi 34B (Base) | 70.8 | #972 |
| 14 | Yi-34Bx2-MoE-60B-DPO | 70.64 | #714 |
| 15 | Nous-Hermes-2-Yi-34B | 70.56 | #812 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-chinese-llm-winogrande · How It Works · Data refreshed daily, snapshot 2026-10-20.