List your company

Interactive Decision Making on WebShop (Seen)

62.3Average RewardGRASP
22.67632.96343.2553.537Apr 20, 2026

Evaluation results

MethodLinks
GRASPModel=Claude-4-Sonnet2026.0462.314.7
GRASPModel=GPT-4.12026.0455.216.8
GRASPModel=Gemini 2.5 Pro2026.045314.9
GRASPModel=GLM-52026.045215.4
GRASPModel=Kimi-K2.52026.0451.616.4
GRASPModel=DeepSeek V3.22026.0446.217.8
ReAct + SkillsModel=Gemini 2.5 Pro2026.044418.2
ReAct + SkillsModel=Claude-4-Sonnet2026.0442.916
GRASPModel=Qwen3-235B2026.0442.318.2
ReAct + SkillsModel=GPT-4.12026.0441.617.8
ReAct + SkillsModel=DeepSeek V3.22026.0440.221.3
ReAct + SkillsModel=GLM-52026.0440.116.6
ReAct + SkillsModel=Kimi-K2.52026.0438.517.9
ReflexionModel=Gemini 2.5 Pro2026.0438.219.9
ReAct + SkillsModel=Qwen3-235B2026.0437.118.7
GRASPModel=o4 Mini2026.0436.218.8
ReflexionModel=DeepSeek V3.22026.0435.322.4
ReflexionModel=GPT-4.12026.0434.620.1
ReflexionModel=Claude-4-Sonnet2026.0434.218
ReflexionModel=GLM-52026.0433.618.6
ReAct + SkillsModel=o4 Mini2026.0433.419.9
ExpeLModel=Claude-4-Sonnet2026.0433.416.6
ExpeLModel=Gemini 2.5 Pro2026.0433.119.3
ReActModel=Claude-4-Sonnet2026.0432.819.8
ExpeLModel=GPT-4.12026.0432.618.4
ReflexionModel=Qwen3-235B2026.0432.420.6
ExpeLModel=GLM-52026.0431.817.2
ReActModel=Gemini 2.5 Pro2026.0431.722.1
ReActModel=DeepSeek V3.22026.0431.624.1
ReflexionModel=Kimi-K2.52026.0431.619.8
ExpeLModel=Qwen3-235B2026.0430.819.2
ReActModel=GPT-4.12026.0430.421.8
ExpeLModel=Kimi-K2.52026.0430.218.6
ReflexionModel=o4 Mini2026.0429.420.5
ReActModel=GLM-52026.0429.420.4
ExpeLModel=DeepSeek V3.22026.0429.224
ReActModel=Qwen3-235B2026.0428.622.4
ReActModel=Kimi-K2.52026.0427.821.6
ExpeLModel=o4 Mini2026.0426.721.9
ReActModel=o4 Mini2026.0424.222