List your company

Household Manipulation on ALFWorld (Seen)

84.65Average RewardSkillReranker
47.126856.868466.6176.3516Jul 7, 2026

Evaluation results

MethodLinks
SkillRerankerBackbone Model=DeepSeek-v4-Flash2026.0784.6515.48
SkillRouterBackbone Model=DeepSeek-v4-Flash2026.0780.7216.31
SkillRerankerBackbone Model=Qwen3.6-27B2026.0778.5712.06
LLM-as-selectorBackbone Model=DeepSeek-v4-Flash2026.0775.3617.21
LLM-as-selectorBackbone Model=Qwen3.6-27B2026.0774.2912.61
SkillRouterBackbone Model=Qwen3.6-27B2026.0772.512.89
Graph of SkillsBackbone Model=Qwen3.6-27B2026.0770.7213.62
Graph of SkillsBackbone Model=DeepSeek-v4-Flash2026.0770.3617.55
SkillRerankerBackbone Model=GPT-5.4-Mini2026.0767.517.55
SkillRouterBackbone Model=GPT-5.4-Mini2026.0762.517.64
Graph of SkillsBackbone Model=GPT-5.4-Mini2026.0758.5720.04
LLM-as-selectorBackbone Model=GPT-5.4-Mini2026.0748.5719.62