List your company

General Assistant Tasks on GAIA

46.7Success RateMiniMax-M2.1
7.38817.59427.838.006Feb 3, 2026

Evaluation results

MethodLinks
MiniMax-M2.1Intervention Mechanism=Baseline, Calibration=N/A2026.0246.7-30
GLM-4.7Intervention Mechanism=Baseline, Calibration=N/A2026.0234.4-4.4
GLM-4.7Intervention Mechanism=Append, Calibration=Calibrated2026.0231.1-4.4
GLM-4.7Intervention Mechanism=Rollback, Calibration=Calibrated2026.0227.8-4.4
GLM-4.7Intervention Mechanism=Rollback, Calibration=Uncalibrated2026.0223.3-4.4
GLM-4.7Intervention Mechanism=Append, Calibration=Uncalibrated2026.0223.3-4.4
Qwen-3-8BIntervention Mechanism=Baseline, Calibration=N/A2026.0218.9-4.4
MiniMax-M2.1Intervention Mechanism=Rollback, Calibration=Calibrated2026.0216.7-30
Qwen-3-8BIntervention Mechanism=Rollback, Calibration=Uncalibrated2026.0214.5-4.4
MiniMax-M2.1Intervention Mechanism=Append, Calibration=Calibrated2026.0214.4-30
MiniMax-M2.1Intervention Mechanism=Rollback, Calibration=Uncalibrated2026.0213.3-30
Qwen-3-8BIntervention Mechanism=Rollback, Calibration=Calibrated2026.0212.2-4.4
MiniMax-M2.1Intervention Mechanism=Append, Calibration=Uncalibrated2026.0212.2-30
Qwen-3-8BIntervention Mechanism=Append, Calibration=Calibrated2026.0210-4.4
Qwen-3-8BIntervention Mechanism=Append, Calibration=Uncalibrated2026.028.9-4.4