Detailed breakdown of individual task performance across different models.
Task Name (24 tasks) | MiniMax-M3 | claude-4-6-sonnet | claude-5-sonnet | deepseek-4-pro | gemini-3.5-flash | gemini-3.5-flash | glm-5.2 |
|---|---|---|---|---|---|---|---|
| 119.6s | 179.3s | - | - | - | 172.8s | 410.6s | |
| 397.8s | 189.4s | - | - | - | 124.2s | 603.5s | |
| 251.0s | 159.6s | - | - | - | 289.0s | 320.4s | |
| 443.2s | 184.0s | - | - | - | 328.3s | 604.9s | |
| 122.2s | 184.7s | - | - | - | 180.1s | 420.0s | |
| 364.8s | 200.4s | - | - | - | 324.4s | 534.4s | |
| 356.3s | 319.0s | - | - | - | 467.7s | 603.5s | |
| 226.3s | 222.9s | - | - | - | 296.0s | 531.3s | |
| 199.1s | 157.9s | - | - | - | 182.6s | 346.6s | |
| 211.3s | 257.3s | - | - | - | 189.6s | 432.0s | |
| 295.1s | 200.0s | - | - | - | 169.0s | 411.7s | |
| 211.6s | 123.0s | - | - | - | 238.5s | 603.5s | |
| 472.5s | 255.6s | - | - | - | 261.4s | 596.5s | |
- | - | 567.5s | 603.5s | 603.8s | - | - | |
- | - | 423.8s | 603.6s | 397.7s | - | - | |
- | - | 495.1s | 561.6s | 345.7s | - | - | |
- | - | 480.9s | 224.3s | 327.0s | - | - | |
- | - | 398.8s | 346.0s | 413.6s | - | - | |
- | - | 374.5s | 488.9s | 604.0s | - | - | |
- | - | 400.8s | 424.3s | 523.2s | - | - | |
- | - | 473.9s | 399.9s | 421.0s | - | - | |
- | - | 362.5s | 214.2s | 485.0s | - | - | |
| 366.0s | 242.6s | - | - | - | 562.4s | 604.3s | |
| 543.7s | 140.9s | - | - | - | 187.8s | 213.4s |