Robotic Task Planning on G-Dataset zero-shot
94.5TSRAIDE
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| AIDEClosed-loop=true, Affordance analysis=true, Real-time execution=true, Zero-shot=true2026.02 | 94.5 | 88 | 89 | 83 | 64 | 9.7 | |
| IntroPlanClosed-loop=false, Affordance analysis=false, Real-time execution=false, Zero-shot=true2026.02 | 82 | — | — | — | — | 0.04 | |
| MOKAClosed-loop=false, Affordance analysis=true, Real-time execution=false, Zero-shot=true2026.02 | 81.5 | 57.5 | 53.5 | 49 | — | 0.03 | |
| RobopointClosed-loop=false, Affordance analysis=false, Real-time execution=true, Zero-shot=true2026.02 | 64 | 38 | 34 | 21.5 | 4 | 0.14 | |
| GPT-5Closed-loop=false, Affordance analysis=false, Real-time execution=false, Zero-shot=true2026.02 | 50.5 | 34.5 | 37.5 | 29.5 | 12 | 0.03 | |
| SayCanClosed-loop=true, Affordance analysis=true, Real-time execution=false, Zero-shot=true2026.02 | 42.5 | — | — | — | — | 0.04 | |
| Qwen3-VLClosed-loop=false, Affordance analysis=false, Real-time execution=false, Zero-shot=true2026.02 | 42 | 23.5 | 13.5 | 12 | 8 | 0.04 | |
| MolmoClosed-loop=false, Affordance analysis=false, Real-time execution=false, Zero-shot=true2026.02 | 10.5 | 6.5 | 1 | 0.5 | 0 | 0.05 | |
| MagmaClosed-loop=false, Affordance analysis=false, Real-time execution=true, Zero-shot=true2026.02 | 1.5 | 0 | 0.5 | 0 | 0 | 1.03 |