| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Aerial Image Classification | AIDER v2 (test) | F1 Score0.966 | 41 | |
| Code Editing | Aider whole format | Average Tries1.5 | 17 | |
| Aerial Image Classification | AIDER (test) | F1 Score81.57 | 12 | |
| Image Classification | AIDER v1 (test) | F1 Score95 | 12 | |
| Aerial Image Recognition | AIDER latest (test) | F1 Score95 | 11 | |
| Code Generation | Aider Polyglot | Pass@359 | 9 | |
| Coding | Aider | Score55.64 | 5 | |
| Image Classification | AIDER (test) | F1 Score- | 0 |