Embodied Task Planning on ALFWorld (test)
98.7Success Rate (Avg)AEC
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| AECModel Category=LLM2026.02 | 98.7 | 100 | 100 | 97 | 95 | 100 | 100 | |
| WALL-E2.0Model Category=LLM2026.02 | 98.3 | 100 | 100 | 96 | 100 | 100 | 94 | |
| RAFAModel Category=LLM2026.02 | 95 | 100 | 97 | 91 | 95 | 100 | 82 | |
| WALL-EModel Category=LLM2026.02 | 95 | 100 | 97 | 100 | 86 | 85 | 100 | |
| AdaPlannerModel Category=LLM2026.02 | 91 | 100 | 100 | 89 | 100 | 97 | 47 | |
| Human Performance2026.02 | 91 | — | — | — | — | — | — | |
| ReflexionModel Category=LLM2026.02 | 86 | 92 | 94 | 70 | 81 | 90 | 88 | |
| EMMAModel Category=VLM2026.02 | 82 | 71 | 94 | 85 | 83 | 88 | 67 | |
| AutoGenModel Category=LLM2026.02 | 77 | 92 | 74 | 78 | 86 | 83 | 41 | |
| DEPSModel Category=LLM2026.02 | 76 | 93 | 50 | 80 | 100 | 100 | 0 | |
| ReActModel Category=LLM2026.02 | 74 | 79 | 54 | 96 | 85 | 83 | 51 | |
| GPT-BUTLERModel Category=LLM2026.02 | 69 | 62 | 81 | 85 | 78 | 50 | 47 | |
| BUTLERModel Category=LLM2026.02 | 26 | 31 | 41 | 60 | 27 | 12 | 29 | |
| InstructBLIPModel Category=VLM2026.02 | 22 | 50 | 26 | 23 | 6 | 17 | 0 | |
| MiniGPT-4Model Category=VLM2026.02 | 16 | 4 | 0 | 19 | 17 | 67 | 6 | |
| LLaMA-AdapterModel Category=VLM2026.02 | 13 | 17 | 10 | 27 | 22 | 0 | 0 | |
| BLIP-2Model Category=VLM2026.02 | 4 | 0 | 6 | 4 | 11 | 6 | 0 |