Detailed breakdown of individual task performance across different models.
Task Name (29 tasks) | claude-4-6-sonnet | claude-5-sonnet | deepseek-4-pro | gemini-3-flash | gemini-3.1-pro | gemini-3.5-flash | glm-4.7 | glm-5.2 |
|---|---|---|---|---|---|---|---|---|
| 62.5s | - | - | 222.6s | 83.7s | - | 99.0s | - | |
| 77.9s | - | - | 102.8s | 83.2s | - | 152.9s | - | |
| 246.5s | - | - | 600.1s | 260.7s | - | 517.7s | - | |
| 135.4s | - | - | 175.5s | 184.0s | - | 345.3s | - | |
| 288.0s | - | - | 239.5s | 256.2s | - | 323.2s | - | |
| 313.1s | - | - | 206.3s | 247.8s | - | 302.5s | - | |
| 207.6s | - | - | 173.9s | 335.7s | - | 411.5s | - | |
| 169.7s | - | - | 185.6s | 180.1s | - | 380.5s | - | |
- | 366.7s | 489.1s | - | - | 596.2s | - | 55.4s | |
- | 183.7s | 180.2s | - | - | 192.7s | - | 245.4s | |
- | 603.5s | 603.5s | - | - | 404.7s | - | 603.5s | |
- | 341.3s | 603.5s | - | - | 329.3s | - | 604.7s | |
- | 366.1s | 604.6s | - | - | 422.0s | - | 605.1s | |
- | 391.1s | 356.5s | - | - | 309.4s | - | 52.6s | |
- | 252.5s | 428.9s | - | - | 321.6s | - | 603.4s | |
- | 237.0s | 292.9s | - | - | 272.2s | - | 603.5s | |
- | 209.8s | 343.8s | - | - | 200.6s | - | 319.7s | |
- | 259.7s | 603.4s | - | - | 334.7s | - | 414.7s | |
- | 263.9s | 603.4s | - | - | 225.3s | - | 603.5s | |
- | 196.6s | 204.0s | - | - | 264.0s | - | 243.4s | |
- | 361.8s | 603.7s | - | - | 473.1s | - | 604.7s | |
- | 604.2s | 604.0s | - | - | 550.3s | - | 360.8s | |
| 221.0s | - | - | 207.1s | 440.2s | - | 600.2s | - | |
| 72.3s | - | - | 98.0s | 70.0s | - | 121.3s | - | |
| 114.7s | - | - | 139.9s | 68.8s | - | 199.4s | - | |
| 28.2s | - | - | 45.2s | 43.2s | - | 77.3s | - | |
| 54.3s | - | - | 83.5s | 81.6s | - | 128.7s | - | |
| 141.1s | - | - | 193.3s | 171.2s | - | 484.1s | - | |
| 424.7s | - | - | 127.5s | 322.1s | - | 429.7s | - |