CPCD-Bench — leaderboard
Metric: SR (LLM-as-a-Judge) (self-reported). Source: benchmarklist.com. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 4.78 |
| 2 | Gemini 3 Flash (Preview) | 4.46 |
| 3 | DeepSeek V3.2 | 4.4 |
| 4 | GLM-5.1 | 4.2 |
| 5 | MiniMax-M2.7 | 4.17 |
| 6 | Gemini 2.5 Flash | 3.97 |
| 7 | Qwen 3 8B | 3.63 |
Interactive version: theaggregate.ai/benchmark?slug=cpcd-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.