Open Chinese LLM - C-Eval Semantic: leaderboard
The "C-Eval Semantic" 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 | Qwen 2 72B Instruct | 94.12 | #576 |
| 2 | Qwen 2 72B | 93.47 | #521 |
| 3 | Rhea-72B-v0.5 | 91.35 | #556 |
| 4 | free-evo-qwen72B-v0.8-re | 91.21 | #435 |
| 5 | Qwen 1.5 72B Chat | 91.14 | #776 |
| 6 | Le_Triomphant-ECE-TW3 | 91.1 | #559 |
| 7 | Qwen 1.5 32B Chat | 90.78 | #816 |
| 8 | Smaug-34B-v0.1 | 90.75 | #723 |
| 9 | Luminex-34B-v0.2 | 90.75 | #696 |
| 10 | YiSM-blossom5.1-34B-SLERP | 90.64 | #591 |
| 11 | UNA-SimpleSmaug-34B-v1beta | 90.6 | #712 |
| 12 | Smaug-72B-v0.1 | 90.6 | #611 |
| 13 | Yi-34Bx2-MoE-60B-DPO | 90.57 | #714 |
| 14 | Bagel-Hermes-34B-Slerp | 90.39 | #715 |
| 15 | Qwen 1.5 72B | 90.13 | #753 |
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-c-eval-semantic · How It Works · Data refreshed daily, snapshot 2026-10-20.