Chinese Classical Bench: leaderboard
A task from Chinese Classical Bench, evaluating comprehension, translation and reasoning over Classical (literary) Chinese texts.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around May 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 66.21 | #49 |
| 2 | Claude Opus 4.7 (Thinking) | 65.48 | #49 (Claude Opus 4.7) |
| 3 | Claude Sonnet 4.6 | 61.3 | #90 |
| 4 | Qwen 3.5 35B A3B | 59.62 | #256 |
| 5 | GLM-5 | 58.8 | #141 |
| 6 | MiniMax-M2.1 | 58.19 | #289 |
| 7 | DeepSeek V3.2 | 58.16 | #205 |
| 8 | MiniMax-M2.5 | 54.97 | #303 |
| 9 | Qwen3 Coder Next | 54.8 | #326 |
| 10 | Claude Haiku 4.5 (20251001) | 45.98 | #261 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=chinese-classical-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.