WorldModelBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Physical Reasoning Evaluation | WorldModelBench | General Score41.8 | 9 | |
| Video Generation | WorldModelBench | Instruction Score2.18 | 7 | |
| World modeling | WorldModelBench Robot in office scenario (test) | Total Score6.9 | 2 | |
| World modeling | WorldModelBench Outdoor vehicle scenario (test) | Total Score5.8 | 2 | |
| World modeling | WorldModelBench Vehicle FSI scenario (test) | Total Score6.8 | 2 | |
| World modeling | WorldModelBench Robot in office | Instruction Following Score2 | 2 | |
| World modeling | WorldModelBench Outdoor vehicle | INSTR Score1 | 2 | |
| World modeling | WorldModelBench Vehicle FSI | Instruction Following Score2.9 | 2 | |
| World Modeling | WorldModelBench Aggregated across three scenarios | Instruction Score5.9 | 2 |
Showing 9 of 9 rows