CCiV (Form-Aware) - Structural Accuracy: leaderboard
Metric: Structural accuracy (%, 0-100): a poem counts when its line count and the character count of every line exactly match the target template (non-Chinese characters removed) of the standard form; form-aware prompt: the complete structural and tonal template of the standard form is given; 300 prompts (10 historical themes for each of the 30 most frequent Cipai tune patterns), three samples each at temperature 0.7 and top-p 0.95, averaged; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen Max | 78.67 | #367 |
| 2 | GLM-4 Plus | 70 | #373 |
| 3 | DeepSeek R1 | 66.67 | #245 |
| 4 | GPT-4o | 63 | #333 |
| 5 | QwQ-32B | 42.67 | #410 |
| 6 | DeepSeek R1 Distill Qwen 32B | 28.33 | #640 |
| 7 | GPT-4o Mini | 7.33 | #588 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=cciv-form-aware-structural-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-11.