Robot Manipulation on SimplerEnv OOD
64.5Average Success RateTwinBrainVLA
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| TwinBrainVLAVLM Backbone=Qwen3-VL-4B-Instruct2026.01 | 64.5 | 87.5 | 58.3 | 33.3 | 79.1 | — | — | — | — | — | — | |
| TwinBrainVLAVLM Backbone=Qwen2.5-VL-3B-Instruct2026.01 | 58.4 | 83.3 | 41.7 | 31.5 | 77.1 | — | — | — | — | — | — | |
| π0.52026.01 | 57.1 | 49.3 | 64.7 | 44.7 | 69.7 | — | — | — | — | — | — | |
| Isaac-GR00T-N1.6-Bridge2026.01 | 57.1 | 64.5 | 65.5 | 5.5 | 93 | — | — | — | — | — | — | |
| Vanilla VLAVLM Backbone=Qwen3-VL-8B-Instruct2026.01 | 56.3 | 68.7 | 38.5 | 30.2 | 87.9 | — | — | — | — | — | — | |
| Vanilla VLAVLM Backbone=Qwen3-VL-4B-Instruct2026.01 | 55.2 | 87.5 | 50 | 29.2 | 54.2 | — | — | — | — | — | — | |
| VideoVLA2026.01 | 53.1 | 75 | 20.8 | 45.8 | 70.8 | — | — | — | — | — | — | |
| Vanilla VLAVLM Backbone=Qwen2.5-VL-3B-Instruct2026.01 | 52.5 | 74.9 | 44.7 | 9.3 | 81.2 | — | — | — | — | — | — | |
| CogACT2026.01 | 51.3 | 71.7 | 50.8 | 15 | 67.5 | — | — | — | — | — | — | |
| Vanilla VLAVLM Backbone=Qwen2.5-VL-7B-Instruct2026.01 | 44.8 | 68.7 | 35.4 | 16.7 | 62.5 | — | — | — | — | — | — | |
| RoboVLM2026.01 | 42.7 | 50 | 37.5 | 0 | 83.3 | — | — | — | — | — | — | |
| SpatialVLA2026.01 | 34.4 | 20.8 | 20.8 | 25 | 70.8 | — | — | — | — | — | — | |
| Qwen-VLA-Instruct2026.05 | 32 | — | — | — | — | 43.8 | 33.3 | 39.6 | 47.9 | 4.2 | 22.9 | |
| TraceVLA2026.01 | 27.7 | 12.5 | 16.6 | 16.6 | 65 | — | — | — | — | — | — | |
| π02026.01 | 27.1 | 29.1 | 0 | 16.6 | 62.5 | — | — | — | — | — | — | |
| Octo-Smallsize=Small2026.01 | 26.7 | 41.7 | 8.2 | 0 | 56.7 | — | — | — | — | — | — | |
| Qwen-VLA-Base2026.05 | 25.3 | — | — | — | — | 31.3 | 31.6 | 16.7 | 47.1 | 6.3 | 18.8 | |
| Octo-Basesize=Base2026.01 | 17.5 | 15.8 | 12.5 | 0 | 41.7 | — | — | — | — | — | — | |
| π0.52026.05 | 12.6 | — | — | — | — | 26.1 | 0 | 0 | 32.1 | 13 | 4.2 | |
| OpenVLA2026.01 | 4.2 | 4.2 | 0 | 0 | 12.5 | — | — | — | — | — | — | |
| RT-1-X2026.01 | 1.1 | 0 | 4.2 | 0 | 0 | — | — | — | — | — | — | |
| ThinkAct2026.01 | — | 58.3 | 37.5 | 8.7 | 70.8 | — | — | — | — | — | — |