C4STYLI — leaderboard
Metric: Accuracy (C4Styli-T) (self-reported). Source: benchmarklist.com. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 79.9 |
| 2 | DeepSeek V3.2 | 74.5 |
| 3 | O4 Mini | 70.1 |
| 4 | Qwen 2.5 32B Instruct | 68.6 |
| 5 | GPT-4.1 | 68.5 |
| 6 | Qwen 3 14B | 68.5 |
| 7 | Qwen 3 32B | 68 |
| 8 | Qwen 3 8B | 66.1 |
| 9 | Qwen 2.5 14B Instruct | 64.8 |
| 10 | Llama 3 70B Instruct | 62.4 |
| 11 | Gemma 3 27B | 60.4 |
| 12 | Qwen 2.5 7B Instruct | 59.8 |
| 13 | Gemma 3 4B | 55.8 |
| 14 | Gemma 3 12B | 54.7 |
| 15 | Llama 3 8B Instruct | 53.5 |
Interactive version: theaggregate.ai/benchmark?slug=c4styli · How the rankings work · Data refreshed daily, snapshot 2026-07-22.