CMMMU
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Chinese Multi-modal Multi-task Understanding | CMMMU | Accuracy42.5 | 13 | |
| Multi-discipline Multimodal Understanding | CMMMU | Accuracy (EN)41.2 | 4 | |
| Visual Question Answering | CMMMU | Accuracy26.1 | 2 |
Showing 3 of 3 rows