Open Chinese LLM - ARC Challenge: leaderboard
The "ARC Challenge" 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 | free-evo-qwen72B-v0.8-re | 71.16 | #435 |
| 2 | Rhea-72B-v0.5 | 70.99 | #556 |
| 3 | luxia-21.4B-alignment-v1.0 | 69.97 | #965 |
| 4 | Le_Triomphant-ECE-TW3 | 69.2 | #559 |
| 5 | Smaug-72B-v0.1 | 67.66 | #611 |
| 6 | Qwen 2 72B Instruct | 66.47 | #576 |
| 7 | UNA-SimpleSmaug-34B-v1beta | 66.04 | #712 |
| 8 | Smaug-34B-v0.1 | 65.87 | #723 |
| 9 | Luminex-34B-v0.2 | 65.87 | #696 |
| 10 | Luminex-34B-v0.1 | 65.78 | #697 |
| 11 | luxia-21.4B-alignment-v1.2 | 64.25 | #1012 |
| 12 | Yi-34Bx2-MoE-60B-DPO | 64.08 | #714 |
| 13 | Qwen 2 72B | 63.74 | #521 |
| 14 | Yi-1.5-34B-Chat-16K | 63.74 | #824 |
| 15 | Bagel-Hermes-34B-Slerp | 63.14 | #715 |
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-arc-challenge · How It Works · Data refreshed daily, snapshot 2026-10-20.