Embodied Planning on AI2-THOR
78.35SRSVLL-Stage 3
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SVLL-Stage 3Category=Embodied-Specific2026.03 | 78.35 | 68.53 | 89.64 | 7.22 | 26.34 | |
| SVLL-Stage 2Category=Embodied-Specific2026.03 | 74.23 | 62.29 | 84.16 | 8.25 | 29.18 | |
| SVLL (Direct Stage 2)Category=Embodied-Specific2026.03 | 68.04 | 55.24 | 78.37 | 10.31 | 30.65 | |
| SVLL-Stage 1Category=Embodied-Specific2026.03 | 64.95 | 51.18 | 76.42 | 12.37 | 33.42 | |
| Gemini-2.0-flashCategory=Closed-Source VLMs2026.03 | 58.76 | 49.32 | 68.45 | 3.09 | 31.55 | |
| GPT-4oCategory=Closed-Source VLMs2026.03 | 48.45 | 46.83 | 59.68 | 1.03 | 40.32 | |
| RoboBrain2.0-32BCategory=Embodied-Specific2026.03 | 27.84 | 26.98 | 47.39 | 6.19 | 52.61 | |
| Qwen2.5-VL-7BCategory=Open-Source General VLMs2026.03 | 18.56 | 17.85 | 45.13 | 5.15 | 54.87 |