| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal reasoning | ZeroBench | Accuracy26.35 | 22 | |
| Multimodal reasoning | ZeroBench sub | Pass@147.6 | 18 | |
| Image Reasoning | ZeroBench sub | Accuracy24.4 | 14 | |
| Multimodal reasoning | ZeroBench main | Pass@111 | 13 | |
| Math | ZeroBench | Score17.66 | 8 | |
| General Reasoning & Understanding | ZeroBench | Accuracy18.9 | 8 | |
| Visual Puzzles | ZeroBench main | Pass@112 | 7 |