Multi-Task Suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Reasoning | Multi-Task Suite VSP, Maze, TSP, Sudoku, Jigsaw, VisPuzzle | Average Score88.5 | 12 | |
| Multi-task Performance Evaluation | Multi-task Suite D1-D4 (test) | Avg F194 | 11 |
Showing 2 of 2 rows