List your company

Task Success on WebShop

61Real Success ScoreClaude-sonnet-4.5
3.789618.642333.49548.3477Dec 21, 2025

Evaluation results

MethodLinks
Claude-sonnet-4.5World Model=Qwen2.5-7B WorldModel2025.126149500.82
Claude-sonnet-4.5World Model=Llama3.1-8B WorldModel2025.126160550.9
GPT-5World Model=Qwen2.5-7B WorldModel2025.125133.0331.190.61
GPT-5World Model=Llama3.1-8B WorldModel2025.125131.1930.280.59
GPT-4oWorld Model=Qwen2.5-7B WorldModel2025.1229.3617.4316.510.56
GPT-4oWorld Model=Llama3.1-8B WorldModel2025.1229.3623.8122.620.77
Gemini-2.5-flashWorld Model=Qwen2.5-7B WorldModel2025.122521.118.350.73
Gemini-2.5-flashWorld Model=Llama3.1-8B WorldModel2025.122522.0217.430.7
GPT-4.1World Model=Qwen2.5-7B WorldModel2025.1221.1412.2212.220.58
GPT-4.1World Model=Llama3.1-8B WorldModel2025.1221.1419.2717.430.82
GPT-4-turboWorld Model=Qwen2.5-7B WorldModel2025.1217.7314.8911.70.66
GPT-4-turboWorld Model=Llama3.1-8B WorldModel2025.1217.7325.4717.921.01
GPT-4o-miniWorld Model=Qwen2.5-7B WorldModel2025.125.994.850.970.16
GPT-4o-miniWorld Model=Llama3.1-8B WorldModel2025.125.992.7500