List your company

Household Simulation on ALFWorld (out-of-distribution)

75Put Success RateDuSAR
-317.2537.557.75Dec 9, 2025

Evaluation results

MethodLinks
DuSARModel=Llama3.1-70B2025.127561.119.41314.352.937.3
DuSARModel=Gemma3-12B2025.1245.827.812.9134.811.819.4
DuSARModel=Llama3.1-8B2025.1237.522.204.305.911.7
SynapseModel=Gemma3-12B2025.1212.55.516.147.84.8014.5
SynapseModel=Llama3.1-70B2025.1212.516.712.926.19.5013
TRADModel=Llama3.1-70B2025.1212.511.13.28.723.809.9
TRADModel=Gemma3-12B2025.128.311.1034.8009
DuSARModel=Llama2-7B2025.124.2000000.75
SynapseModel=Llama3.1-8B2025.124.216.700003.5
SynapseModel=Llama2-7B2025.120000000
TRADModel=Llama2-7B2025.120000000
TRADModel=Llama3.1-8B2025.120000000