App-based Task Execution on AppWorld Normal
71.4Task Goal Completion (TGC)MIND-Skill
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MIND-SkillSkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.05 | 71.4 | 55.4 | |
| MIND-SkillSkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.05 | 70.8 | 57.1 | |
| Trace2SkillSkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.05 | 70.2 | 51.8 | |
| ACESkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.05 | 69 | 58.9 | |
| Trace2SkillSkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.05 | 67.3 | 55.4 | |
| ACESkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.05 | 65.5 | 55.4 | |
| Skill-extractSkill Generation=Qwen3.5-122B-A10B, Inference Model=Qwen3.5-122B-A10B2026.05 | 63.7 | 46.4 | |
| Skill-extractSkill Generation=GPT-5.4, Inference Model=Qwen3.5-122B-A10B2026.05 | 63.7 | 44.6 | |
| ICLSkill Generation=None, Inference Model=Qwen3.5-122B-A10B2026.05 | 58.9 | 39.3 | |
| ReActSkill Generation=None, Inference Model=Qwen3.5-122B-A10B2026.05 | 55.4 | 35.7 |