List your company

Interactive Task Solving on WebShop

68.36Average Task PerformanceATG
3.432820.288937.14554.0011Jul 2, 2026

Evaluation results

MethodLinks
ATGBackbone=Llama-3-8B2026.0768.36
ATGBackbone=Gemma-7B2026.0764.93
ReActBackbone=GPT-42026.0764.34
ATGBackbone=Mistral-7B2026.0762.75
ReActBackbone=GPT-3.5-Turbo2026.0743.57
PoGBackbone=Llama-3-8B2026.0731.66
ToTBackbone=Llama-3-8B2026.0727.4
CAMELBackbone=Llama-3-8B2026.0724.85
PoGBackbone=Mistral-7B2026.0724.18
ReflexionBackbone=Llama-3-8B2026.0722.73
ToTBackbone=Mistral-7B2026.0720.31
ReActBackbone=Llama-3-8B2026.0719.32
CAMELBackbone=Mistral-7B2026.0718.05
ReflexionBackbone=Mistral-7B2026.0716.64
ReActBackbone=Mistral-7B2026.0714.63
PoGBackbone=Gemma-7B2026.0712.56
ToTBackbone=Gemma-7B2026.0710.84
CAMELBackbone=Gemma-7B2026.079.48
ReflexionBackbone=Gemma-7B2026.077.71
ReActBackbone=Gemma-7B2026.075.93