General Assistant Tasks on GAIA
46.7Success RateMiniMax-M2.1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MiniMax-M2.1Intervention Mechanism=Baseline, Calibration=N/A2026.02 | 46.7 | -30 | |
| GLM-4.7Intervention Mechanism=Baseline, Calibration=N/A2026.02 | 34.4 | -4.4 | |
| GLM-4.7Intervention Mechanism=Append, Calibration=Calibrated2026.02 | 31.1 | -4.4 | |
| GLM-4.7Intervention Mechanism=Rollback, Calibration=Calibrated2026.02 | 27.8 | -4.4 | |
| GLM-4.7Intervention Mechanism=Rollback, Calibration=Uncalibrated2026.02 | 23.3 | -4.4 | |
| GLM-4.7Intervention Mechanism=Append, Calibration=Uncalibrated2026.02 | 23.3 | -4.4 | |
| Qwen-3-8BIntervention Mechanism=Baseline, Calibration=N/A2026.02 | 18.9 | -4.4 | |
| MiniMax-M2.1Intervention Mechanism=Rollback, Calibration=Calibrated2026.02 | 16.7 | -30 | |
| Qwen-3-8BIntervention Mechanism=Rollback, Calibration=Uncalibrated2026.02 | 14.5 | -4.4 | |
| MiniMax-M2.1Intervention Mechanism=Append, Calibration=Calibrated2026.02 | 14.4 | -30 | |
| MiniMax-M2.1Intervention Mechanism=Rollback, Calibration=Uncalibrated2026.02 | 13.3 | -30 | |
| Qwen-3-8BIntervention Mechanism=Rollback, Calibration=Calibrated2026.02 | 12.2 | -4.4 | |
| MiniMax-M2.1Intervention Mechanism=Append, Calibration=Uncalibrated2026.02 | 12.2 | -30 | |
| Qwen-3-8BIntervention Mechanism=Append, Calibration=Calibrated2026.02 | 10 | -4.4 | |
| Qwen-3-8BIntervention Mechanism=Append, Calibration=Uncalibrated2026.02 | 8.9 | -4.4 |