CCiV (Direct, Standard Form) - Tonal Accuracy: leaderboard
Metric: Tonal accuracy (%, 0-100): share of characters whose level or oblique tone (Zhonghua Xinyun standard) matches the template's tonal pattern, zero for a structurally wrong poem of the standard form; direct prompt: only the Cipai name and the theme; 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 | DeepSeek R1 | 53.13 | #245 |
| 2 | GPT-4o | 49.36 | #333 |
| 3 | GLM-4 Plus | 37.45 | #373 |
| 4 | Qwen Max | 37.05 | #367 |
| 5 | DeepSeek R1 Distill Qwen 32B | 24.92 | #640 |
| 6 | QwQ-32B | 11.29 | #410 |
| 7 | GPT-4o Mini | 0.02 | #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-direct-standard-form-tonal-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-11.