| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Image Classification | Others | Accuracy93.91 | 20 | |
| Function Calling | Others (SealTools, OpenFunc, ToolAlpaca) | Overall Accuracy87.4 | 12 | |
| Natural Language Understanding | Others (WG, Yelp, SciTail, PAWS) | WG Accuracy62.3 | 11 | |
| Image Classification | Others | CIFAR-10 Accuracy98.8 | 10 | |
| Multiple-Choice Question Answering | OTHERS 4-Choice | Delta Acc0 | 6 |