Robot Manipulation on SimplerEnv WidowX (test)
79.2Task Success Rate (Spoon on Towel)pi_0.5
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| pi_0.5weight_threshold=0.52026.06 | 79.2 | — | — | 37.5 | — | 37.5 | — | 70.8 | 56.2 | — | |
| PoLAR2026.06 | 75 | — | — | 58.3 | — | 37.5 | — | 79.2 | 62.5 | — | |
| Flat (5 × 16)latent_shape=5 × 162026.06 | 70.8 | — | — | 45.8 | — | 29.2 | — | 45.8 | 47.9 | — | |
| PoLAR (dir-only)mode=direction-only2026.06 | 66.7 | — | — | 45.8 | — | 33.3 | — | 62.5 | 52.1 | — | |
| SmolVLA2026.06 | 66.7 | — | — | 41.7 | — | 41.7 | — | 70.8 | 55.2 | — | |
| GR00T-N12026.03 | 62.5 | 83.3 | 54.2 | 45.8 | 70.8 | 16.7 | 41.7 | 20.8 | 36.5 | — | |
| GR00T-N1Pre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 62.5 | 83.3 | 54.2 | 45.8 | 70.8 | 16.7 | 41.7 | 20.8 | 49.5 | — | |
| Flat (4 × 32)latent_shape=4 × 322026.06 | 62.5 | — | — | 37.5 | — | 16.7 | — | 37.5 | 38.5 | — | |
| UniVLA2026.06 | 62.5 | — | — | 45.8 | — | 33.3 | — | 45.8 | 46.9 | — | |
| GAM2026.05 | 58.3 | 91.7 | 66.7 | 37.5 | 79.2 | 41.7 | 95.8 | 87.5 | 56.3 | — | |
| Fact.variant=Factorized2026.06 | 58.3 | — | — | 50 | — | 29.2 | — | 33.3 | 42.7 | — | |
| Villa-X2026.06 | 58.3 | — | — | 54.2 | — | 8.3 | — | 41.7 | 40.6 | — | |
| LLaDA-VLA2026.03 | 56.9 | — | — | 76.3 | — | 30.6 | — | 58.3 | 55.5 | 160 | |
| Dream-VLA + Block DiffusionAcceleration Module=Block Diffusion2026.03 | 54.1 | 83.3 | 66.7 | 45.8 | 83.3 | 29.1 | 95.8 | 91.6 | 55.2 | 226.4 | |
| Dream-VLA + Fast-dVLAAcceleration Module=Fast-dVLA2026.03 | 54.1 | 83.3 | 62.5 | 54.1 | 83.3 | 37.5 | 100 | 91.6 | 59.3 | 366.4 | |
| Octo-Small2026.05 | 47.2 | 77.8 | 27.8 | 9.7 | 40.3 | 4.2 | 87.5 | 56.9 | 29.5 | — | |
| Octo-SmallPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 47.2 | 77.8 | 27.8 | 9.7 | 40.3 | 4.2 | 87.5 | 56.9 | 43.9 | — | |
| Dream-VLA2026.03 | 45.8 | 79.2 | 62.5 | 45.8 | 83.3 | 25 | 100 | 87.5 | 51 | 100.1 | |
| RoboVLMs2026.05 | 45.8 | 70.8 | 33.3 | 20.8 | 54.2 | 4.2 | 91.7 | 79.2 | 37.5 | — | |
| Dream-VLA + Fast-dLLMAcceleration Module=Fast-dLLM2026.03 | 41.7 | 70.8 | 54.2 | 37.5 | 70.8 | 20.8 | 83.3 | 66.6 | 41.7 | 214.2 | |
| BEAST2026.05 | 41.7 | 66.7 | 37.5 | 25 | 50 | 20.8 | 87.5 | 75 | 37.5 | — | |
| OpenVLA-OFT2026.05 | 34.5 | — | — | 30 | — | 30 | — | 72.5 | 41.8 | — | |
| DDVLA2026.03 | 29.2 | 70.8 | 58.3 | 29.2 | 62.5 | 20.8 | 91.7 | 70.8 | 37.5 | 152.8 | |
| π0-FAST2026.05 | 29.2 | 33.3 | 25 | 20.8 | 37.5 | 12.5 | 75 | 66.7 | 32.3 | — | |
| RoboVLMPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 29.2 | 54.2 | 25 | 25 | 45.8 | 12.5 | 58.3 | 58.3 | 38.5 | — | |
| Discrete Diffusion VLAPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 29.2 | 70.8 | 58.3 | 29.2 | 62.5 | 20.8 | 91.7 | 70.8 | 54.2 | — | |
| LAPA2026.06 | 29.2 | — | — | 29.2 | — | 8.3 | — | 41.7 | 27.1 | — | |
| π02026.03 | 29.1 | 45.8 | 25 | 0 | 50 | 16.6 | 91.6 | 62.5 | 27.1 | — | |
| π0-FAST2026.03 | 29.1 | 62.5 | 58.5 | 21.9 | 54 | 10.8 | 83.3 | 66.6 | 32.1 | 107.5 | |
| π02026.05 | 29.1 | — | — | 0 | — | 16.6 | — | 62.5 | 27.1 | — | |
| π0Pre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 29.1 | 45.8 | 25 | 0 | 50 | 16.7 | 91.6 | 62.5 | 40.1 | — | |
| π0-FASTPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 29.1 | 62.5 | 58.5 | 21.9 | 54 | 10.8 | 83.3 | 66.6 | 48.3 | — | |
| RoboVLM2026.03 | 20.8 | 37.5 | 33.3 | 25 | 8.3 | 8.3 | 0 | 0 | 13.5 | — | |
| SpatialVLA2026.03 | 16.7 | 20.8 | 29.2 | 25 | 62.5 | 29.2 | 100 | 100 | 42.7 | — | |
| SpatialVLA2026.05 | 16.7 | 20.8 | 29.2 | 25 | 62.5 | 29.2 | 100 | 100 | 42.7 | — | |
| OpenVLA-OFT2026.03 | 12.5 | 50 | 41.7 | 4.2 | 70.8 | 20.8 | 91.7 | 37.5 | 18.8 | — | |
| Octo-Base2026.05 | 12.5 | 34.7 | 52.8 | 8.3 | 31.9 | 0 | 66.7 | 43.1 | 16 | — | |
| Octo-BasePre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 12.5 | 34.7 | 52.8 | 8.3 | 31.9 | 0 | 66.7 | 43.1 | 31.3 | — | |
| OpenVLA-OFTPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 12.5 | 50 | 41.7 | 4.2 | 70.8 | 8.3 | 91.7 | 37.5 | 39.6 | — | |
| RT-1-XPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 0 | 16.7 | 20.8 | 4.2 | 8.3 | 0 | 0 | 0 | 6.3 | — | |
| OpenVLAPre-training=OXE dataset, Fine-tuning=BridgeData V22025.08 | 0 | 4.1 | 33 | 0 | 12.5 | 0 | 8.3 | 4.1 | 7.8 | — |