RR
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reasoning / Reward | RR | RR Average73.2 | 18 | |
| Multimodal Reasoning | RR | Accuracy37.3 | 12 | |
| Open world region level image recognition | RR-7K | Semantic Similarity69.1 | 5 | |
| Relationship-controlled Image Generation | RR | Position Control (Qwen)0.697 | 4 |
Showing 4 of 4 rows