Chinese Classical Bench - Fill-In Exact: leaderboard
The "Fill-In Exact" subtask of Chinese Classical Bench. A task from Chinese Classical Bench, evaluating comprehension, translation and reasoning over Classical (literary) Chinese texts.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 (Thinking) | 88 | #49 (Claude Opus 4.7) |
| 2 | Claude Opus 4.7 | 86 | #49 |
| 3 | Claude Sonnet 4.6 | 70 | #90 |
| 4 | MiniMax-M2.1 | 63 | #289 |
| 5 | MiniMax-M2.5 | 59 | #303 |
| 6 | DeepSeek V3.2 | 55 | #205 |
| 7 | Qwen3 Coder Next | 52 | #326 |
| 8 | GLM-5 | 45 | #141 |
| 9 | Qwen 3.5 35B A3B | 38 | #256 |
| 10 | Claude Haiku 4.5 (20251001) | 35 | #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-fill-in-exact · How It Works · Data refreshed daily, snapshot 2026-10-20.