Open Chinese LLM - HellaSwag: leaderboard
The "HellaSwag" 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 | 80.26 | #965 |
| 2 | free-evo-qwen72B-v0.8-re | 78.09 | #435 |
| 3 | Rhea-72B-v0.5 | 77.8 | #556 |
| 4 | luxia-21.4B-alignment-v1.2 | 77.12 | #1012 |
| 5 | Le_Triomphant-ECE-TW3 | 76.54 | #559 |
| 6 | Smaug-72B-v0.1 | 75 | #611 |
| 7 | Qwen 2 72B Instruct | 73.93 | #576 |
| 8 | Qwen 2 72B | 73.26 | #521 |
| 9 | deepseek-llm-67B-base | 72.83 | #973 |
| 10 | Qwen 1.5 72B Chat | 72.16 | #776 |
| 11 | Luminex-34B-v0.2 | 71.14 | #696 |
| 12 | Smaug-34B-v0.1 | 71.11 | #723 |
| 13 | UNA-SimpleSmaug-34B-v1beta | 71.08 | #712 |
| 14 | Luminex-34B-v0.1 | 70.93 | #697 |
| 15 | Qwen 1.5 32B Chat | 70.43 | #816 |
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-hellaswag · How It Works · Data refreshed daily, snapshot 2026-10-20.