AB-DB
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| FILES | AB-DB | Diff Recall48.8 | 9 | |
| STRING | AB-DB | LLM Judge Accuracy28.7 | 9 | |
| Agentic Task Solving | AB-DB | Pass@351.1 | 9 | |
| File Editing | AB-DB | Exact Match46.6 | 9 | |
| String Extraction | AB-DB | Exact Match26.2 | 9 |
Showing 5 of 5 rows