| Rank | Model | Score |
|---|---|---|
| 1 | grok-4-5 | 0.505 |
| 2 | claude-sonnet-5 | 0.497 |
| 3 | claude-opus-4-8 | 0.492 |
| 4 | claude-fable-5 | 0.487 |
| 5 | gpt-5-6 | 0.451 |
| 6 | gpt-5-5 | 0.445 |
| 7 | minimax-m3 | 0.385 |
| 8 | claude-sonnet-4-6 | 0.373 |
| 9 | kimi-k2-7-code | 0.367 |
| 10 | glm-5-2 | 0.316 |
| 11 | qwen3-6-plus | 0.313 |
| 12 | deepseek-v4-pro | 0.307 |
| 13 | qwen3-7-max | 0.296 |
| 14 | hy3 | 0.288 |
| 15 | seed-2-1-pro | 0.286 |
| 16 | gemini-3-1-pro | 0.279 |
| 17 | gpt-5-4 | 0.272 |
| 18 | glm-5-1 | 0.267 |
| 19 | kimi-k2-6 | 0.255 |
| 20 | gpt-5-3-codex | 0.203 |
| 21 | grok-4-20 | 0.08 |
1 phaseActive