List your company

Reward Modeling on OSWorld Verified Class-Balanced Scripts 1.0 (test)

79.2PrecisionVAGEN
73.68875.11976.5577.981Jan 31, 2026

Evaluation results

MethodLinks
VAGENVerified Agent Backbone=Claude-Sonnet-4.52026.0179.294.486.283.1
AndroidGenVerified Agent Backbone=Claude-Sonnet-4.52026.0178.876.677.774.4
WebRLVerified Agent Backbone=Claude-Sonnet-4.52026.0177.876.777.373.9
FullTrajEvalVerified Agent Backbone=Claude-Sonnet-4.52026.0175.690.182.278.1
ZeroGUIVerified Agent Backbone=Claude-Sonnet-4.52026.0175.189.281.577.2
DistRLVerified Agent Backbone=Claude-Sonnet-4.52026.0174.974.174.570.9
DigiRLVerified Agent Backbone=Claude-Sonnet-4.52026.0173.973.573.770.2