Multimodal Understanding on ScienceQA, TextVQA, GQA, VizWiz, and ImageNet
33.47Accuracy
MoDE
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.12 | 33.47 | 25.99 | 22.78 | |
2025.12 | 33.01 | 30.77 | 24.31 | |
2025.12 | 32.86 | 30.95 | 24.46 | |
2025.12 | 32.62 | 27.66 | 24.7 | |
2025.12 | 31.92 | 6.82 | 25.4 | |
2025.12 | 28.43 | 35.33 | 28.57 | |
2025.12 | 22.48 | - | 34.84 |