Embodied Task Planning on EB-Habitat (OOD)
59Success RateGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.04 | 59 | |
| Claude-3.7-Sonnet2026.04 | 58.7 | |
| Gemini-1.5-Pro2026.04 | 56.3 | |
| RoboAgent2026.04 | 22.3 | |
| RoboGPT-R12026.04 | 22 | |
| REBP2026.04 | 20 |
| Method | Links | |
|---|---|---|
| GPT-4o2026.04 | 59 | |
| Claude-3.7-Sonnet2026.04 | 58.7 | |
| Gemini-1.5-Pro2026.04 | 56.3 | |
| RoboAgent2026.04 | 22.3 | |
| RoboGPT-R12026.04 | 22 | |
| REBP2026.04 | 20 |