Robotic Manipulation on SimplerEnv (Specific Task Success Rates)
87.5Success Rate: Spoon on TowelOneVLA
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OneVLAParams=3B, Unified=Yes2026.05 | 87.5 | 37.5 | 50 | 83.3 | 64.5 | |
| π02026.06 | 84.6 | 55.8 | 47.9 | 85.4 | 68.4 | |
| MemoryVLA++2026.06 | 83.3 | 66.7 | 45.8 | 100 | 73.9 | |
| STORM2025.12 | 79.2 | 50 | 12.5 | 62.5 | 51 | |
| GR00T-N1.52026.06 | 75.3 | 54.3 | 57 | 61.3 | 61.9 | |
| CogACT2025.12 | 75 | 45.9 | 12.5 | 58.3 | 47.9 | |
| VideoVLA2026.05 | 75 | 20.8 | 45.8 | 70.8 | 53.1 | |
| VideoVLA2026.06 | 75 | 20.8 | 45.8 | 70.8 | 53.1 | |
| MemoryVLA2026.06 | 75 | 75 | 37.5 | 100 | 71.9 | |
| CogACT2026.05 | 71.7 | 50.8 | 15 | 67.5 | 51.3 | |
| CronusVLA2026.06 | 66.7 | 54.2 | 20.8 | 100 | 60.4 | |
| Afford-VLA2026.05 | 66.6 | 54.2 | 14.6 | 96.8 | 58.1 | |
| Isaac-GR00T-N1.6-Bridge2026.05 | 64.5 | 65.5 | 5.5 | 93 | 57.1 | |
| π0-FASTvariant=FAST2026.06 | 62.5 | 29.2 | 20.8 | 83.3 | 49 | |
| CogACT2026.06 | 58.3 | 45.8 | 29.2 | 95.8 | 57.3 | |
| VLA-ReasonerBase Model=Octo-Small, World Model Parameter size=600M2025.09 | 50 | 32 | 13 | 54 | 37.3 | |
| RoboVLM2026.05 | 50 | 37.5 | 0 | 83.3 | 42.7 | |
| π0.52026.05 | 49.3 | 64.7 | 44.7 | 69.7 | 57.1 | |
| RoboVLMs2026.06 | 45.8 | 20.8 | 4.2 | 79.2 | 37.5 | |
| DreamVLA2026.06 | 45.8 | 45.8 | 25 | 87.5 | 51 | |
| Language-Based Action RepresentationsModel size=3B2025.12 | 44 | 36.2 | 0 | 61.1 | 35.3 | |
| Octo-SmallParameter size=27M, Action chunking=12025.09 | 43 | 10 | 5 | 48 | 26.5 | |
| OctoModel Size=Small2025.12 | 41.7 | 8.2 | 0 | 56.7 | 26.7 | |
| Octo-Small2025.12 | 41.7 | 8.2 | 0 | 56.7 | 26.7 | |
| Mimic-video2026.06 | 41.7 | 54.2 | 29.2 | 100 | 56.3 | |
| ECoT2025.12 | 40.2 | 11.7 | 0 | 28.4 | 20.1 | |
| Magma2026.05 | 37.5 | 29.2 | 20.8 | 91.7 | 44.8 | |
| MagmaParams=7B, Unified=No2026.05 | 37.5 | 29.2 | 20.8 | 91.7 | 44.8 | |
| UniVLA-Mani.*Params=7B, Unified=No2026.05 | 37.5 | 33.3 | 4.2 | 66.7 | 35.4 | |
| Magma2026.06 | 37.5 | 29.2 | 20.8 | 91.7 | 44.8 | |
| VLA-ReasonerBase Model=SpatialVLA, World Model Parameter size=600M2025.09 | 35 | 28 | 29 | 75 | 41.8 | |
| OpenVLA-OFT2026.05 | 34.2 | 30 | 30 | 72.5 | 41.8 | |
| OpenVLA-OFTParams=7B, Unified=No2026.05 | 34.2 | 30 | 30 | 72.5 | 41.8 | |
| Language-Based Action RepresentationsModel size=1.5B2025.12 | 30.8 | 20.8 | 0 | 24.4 | 19 | |
| π02026.05 | 29.2 | 62.5 | 29.2 | 91.6 | 53.1 | |
| RoboVLMParams=2B, Unified=No2026.05 | 29.2 | 25 | 12.5 | 58.3 | 31.3 | |
| π0Params=3B, Unified=No2026.05 | 29.1 | 0 | 16.6 | 62.5 | 27.1 | |
| π0-FastParams=3B, Unified=No2026.05 | 29.1 | 21.9 | 10.8 | 66.6 | 48.3 | |
| Language-Based Action RepresentationsModel size=0.5B2025.12 | 21.1 | 24.4 | 0 | 10.7 | 14.1 | |
| SpatialVLA2026.05 | 20.8 | 20.8 | 25 | 70.8 | 34.4 | |
| SpatialVLAParameter size=4B, Action chunking=42025.09 | 18 | 22 | 23 | 73 | 34 | |
| SpatialVLAParams=7B, Unified=No2026.05 | 16.7 | 25 | 29.2 | 100 | 42.7 | |
| SpatialVLA2026.06 | 16.7 | 25 | 29.2 | 100 | 42.7 | |
| OctoModel Size=Base2025.12 | 15.8 | 12.5 | 0 | 41.7 | 17.5 | |
| Octo-Base2025.12 | 15.8 | 12.5 | 0 | 41.7 | 17.5 | |
| Octo-Base2026.05 | 15.8 | 12.5 | 0 | 41.7 | 17.5 | |
| Octo-Basevariant=Base2026.06 | 15.8 | 12.5 | 0 | 41.7 | 17.5 | |
| TraceVLA2026.05 | 12.5 | 16.6 | 16.6 | 65 | 27.7 | |
| Octo-BaseParams=93M, Unified=No2026.05 | 12.5 | 8.3 | 0 | 43.1 | 16 | |
| TraceVLA2026.06 | 12.5 | 16.6 | 16.6 | 65 | 27.7 | |
| OpenVLA-OFTvariant=OFT2026.06 | 12.5 | 4.2 | 4.2 | 100 | 30.2 | |
| OpenVLA2025.12 | 4.2 | 0 | 0 | 12.5 | 4.2 | |
| Openvla2025.12 | 4.2 | 0 | 0 | 12.5 | 4.2 | |
| OpenVLA2026.06 | 4.2 | 0 | 0 | 12.5 | 4.2 | |
| RT-1-X2025.12 | 0 | 4.2 | 0 | 0 | 1.1 | |
| RT1-x2025.12 | 0 | 4.2 | 0 | 0 | 1.1 | |
| RT-1-X2026.05 | 0 | 4.2 | 0 | 0 | 1.1 | |
| RT-1-XParams=35M, Unified=No2026.05 | 0 | 4.2 | 0 | 0 | 1.1 | |
| OpenVLAParams=7B, Unified=No2026.05 | 0 | 0 | 0 | 4.1 | 1 | |
| RT-1-X2026.06 | 0 | 4.2 | 0 | 0 | 1.1 |