Agentic Task on OfficeQA
36Accuracy
Oracle grid best
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 36 | |
2026.06 | 33.8 | |
2026.06 | 26.7 | |
2026.06 | 26.2 | |
2026.06 | 25.6 |
Oracle grid best
| Method | Links | |
|---|---|---|
2026.06 | 36 | |
2026.06 | 33.8 | |
2026.06 | 26.7 | |
2026.06 | 26.2 | |
2026.06 | 25.6 |