| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Logical Reasoning | LogicVista | Accuracy52.8 | 28 | |
| Multimodal Reasoning | LogicVista | Accuracy61.7 | 24 | |
| Logical Reasoning | LogicVista | Pass@156.3 | 19 | |
| Logical Reasoning | LogicVista | Accuracy58.2 | 19 | |
| Multimodal Mathematical Reasoning | LogicVista | Accuracy75.2 | 15 | |
| Logical Reasoning | LogicVista (test) | Accuracy60.3 | 12 | |
| Visual Mathematical Reasoning | LogicVista | Accuracy73.8 | 12 | |
| STEM & Puzzle | LogicVista (test) | Accuracy71.4 | 11 | |
| Universal multi-modal reasoning | LogicVista | Pass@146.53 | 2 |