List your company

Web Agent Interaction on WebShop

88.4ScoreENVRL-GiGPO
20.48838.11955.7573.381Jun 16, 2026

Evaluation results

MethodLinks
ENVRL-GiGPOBackbone Model=Qwen2.5-7B-Instruct2026.0688.476.3
ENVRL-GiGPOBackbone Model=Qwen2.5-1.5B-Instruct2026.0688.274.2
GiGPOBackbone Model=Qwen2.5-7B-Instruct2026.0686.275.2
GiGPOBackbone Model=Qwen2.5-1.5B-Instruct2026.0683.567.4
ENVRL-GRPOBackbone Model=Qwen2.5-1.5B-Instruct2026.068367
ENVRL-GRPOBackbone Model=Qwen2.5-7B-Instruct2026.0681.868.6
GRPOBackbone Model=Qwen2.5-7B-Instruct2026.0679.366.1
GRPOBackbone Model=Qwen2.5-1.5B-Instruct2026.0675.856.8
ReActBackbone Model=Qwen2.5-7B-Instruct2026.0646.219.5
Gemini-2.5-ProBackbone Model=Proprietary Model2026.0642.535.9
ReActBackbone Model=Qwen2.5-1.5B-Instruct2026.0640.111.3
GPT-4oBackbone Model=Proprietary Model2026.0631.823.7
PromptingBackbone Model=Qwen2.5-7B-Instruct2026.0626.47.8
PromptingBackbone Model=Qwen2.5-1.5B-Instruct2026.0623.15.2