Setuptable on VirtualHome livingroom_and_bedroom
82.7Task Success Rate (TSR)Deepseek-R1
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Deepseek-R1Model=Deepseek-R12026.03 | 82.7 | 94.5 | 100 | 51 | |
| Llama3.3-70BModel=Llama3.3-70B2026.03 | 76 | 87 | 60 | 11.8 | |
| GPT-5-miniModel=GPT-5-mini2026.03 | 71.4 | 94 | 100 | 39.2 |