List your company

App-based Task Execution on AppWorld Normal

71.4Task Goal Completion (TGC)MIND-Skill
54.7659.0863.467.72May 9, 2026

Evaluation results

MethodLinks
MIND-SkillSkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.0571.455.4
MIND-SkillSkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.0570.857.1
Trace2SkillSkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.0570.251.8
ACESkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.056958.9
Trace2SkillSkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.0567.355.4
ACESkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.0565.555.4
Skill-extractSkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.0563.746.4
Skill-extractSkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.0563.744.6
ICLSkill Generation=None, Inference Model=Qwen3.5-122B-A10B2026.0558.939.3
ReActSkill Generation=None, Inference Model=Qwen3.5-122B-A10B2026.0555.435.7