List your company

Web Interaction on Mind2Web cross-Task

48.62Action Efficiency (EA)EDV
38.677641.258843.8446.4212Jun 23, 2026

Evaluation results

MethodLinks
EDVBackbone Model=Ensemble2026.0648.6263.143.174.76
Reasoning Bank (RB)Backbone Model=Mimo-V2-Flash, Memory Strategy=RB2026.0646.7761.8342.015.55
Reasoning Bank (RB)Backbone Model=GLM-4.7-FP8, Memory Strategy=RB2026.0644.4657.7840.924.37
RouterBackbone Model=Ensemble2026.0644.3757.0240.284.37
No Memory (NM)Backbone Model=GLM-4.7-FP8, Memory Strategy=NM2026.0642.6455.7438.313.84
No Memory (NM)Backbone Model=Mimo-V2-Flash, Memory Strategy=NM2026.0642.3858.3137.483.21
JudgeBackbone Model=Ensemble2026.0641.375635.143.06
No Memory (NM)Backbone Model=Minimax-M2.1, Memory Strategy=NM2026.0639.9259.1434.193.57
Reasoning Bank (RB)Backbone Model=Minimax-M2.1, Memory Strategy=RB2026.0639.0659.7533.953.17