| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Embodied Task Planning | Robotouille Synchronous | Pass@1 Accuracy97 | 15 | |
| Embodied Task Planning | Robotouille Asynchronous (test) | Pass@1 Accuracy86 | 15 | |
| Robotic Planning | Robotouille Impossible | Solved Percentage100 | 7 | |
| Robotic Planning | Robotouille Hard | Solved Rate58.1 | 7 | |
| Robotic Planning | Robotouille Easy | Solved Rate81 | 7 | |
| Robot task code generation | Robotouille simulator (overall) | Execution Success Rate79 | 3 |