Metric: Variant Aggregation-Pick Coke Can (higher is better)
| # | Model↕ | Variant Aggregation-Pick Coke Can▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SoFar | 0.907 | No | SoFar: Language-Grounded Orientation Bridges Spa... | 2025-02-18 | Code |
| 2 | SpatialVLA | 0.895 | Yes | SpatialVLA: Exploring Spatial Representations fo... | 2025-01-27 | - |
| 3 | Dita-300M | 0.855 | Yes | Dita: Scaling Diffusion Transformer for Generali... | 2025-03-25 | Code |
| 4 | RT-2-X | 0.823 | Yes | RT-2: Vision-Language-Action Models Transfer Web... | 2023-07-28 | Code |
| 5 | RoboVLM | 0.683 | Yes | Towards Generalist Robot Policies: What Matters ... | 2024-12-18 | Code |
| 6 | TraceVLA | 0.6 | Yes | TraceVLA: Visual Trace Prompting Enhances Spatia... | 2024-12-13 | - |
| 7 | OpenVLA | 0.545 | Yes | OpenVLA: An Open-Source Vision-Language-Action M... | 2024-06-13 | Code |
| 8 | RT-1-X | 0.49 | Yes | RT-1: Robotics Transformer for Real-World Contro... | 2022-12-13 | Code |
| 9 | Octo-Base | 0.006 | Yes | Octo: An Open-Source Generalist Robot Policy | 2024-05-20 | - |