List your company

Embodied Household Planning on ALFWorld

87.5Success RateTRIAGE
38.82851.46464.176.736Jun 30, 2026

Evaluation results

MethodLinks
TRIAGEModel=Qwen2.5-7B-Instruct, Judge=Qwen3-8B-thinking, Evidence=true2026.0687.5
TRIAGEModel=Qwen2.5-7B-Instruct, Judge=Qwen3-8B-thinking, Evidence=false2026.0683.1
GRPOModel=Qwen2.5-7B-Instruct2026.0679.6
TRIAGEModel=Qwen2.5-7B-Instruct, Judge=Qwen3-8B no-think2026.0676.8
TRIAGEModel=Qwen3-1.7B-Instruct, Judge=Qwen3-8B-thinking, Evidence=true2026.0656.4
TRIAGEModel=Qwen3-1.7B-Instruct, Judge=Qwen3-8B-thinking, Evidence=false2026.0651.8
GRPOModel=Qwen3-1.7B-Instruct2026.0645.2
TRIAGEModel=Qwen3-1.7B-Instruct, Judge=Qwen3-8B no-think2026.0640.7