Tool-use AI Assistant on GAIA
54.4Accuracy (Text-only)
AutoAgent
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 54.4 | 54.2 | 44.7 | 52.1 | |
2026.03 | 46.6 | 29.2 | 34.2 | 41.2 | |
2026.03 | 35 | 29.2 | 34.2 | 33.9 | |
2026.03 | 34 | 25 | 34.2 | 30.9 | |
2026.03 | 29.1 | 4.2 | 7.9 | 20.6 | |
2026.03 | 29.1 | 0 | 28.9 | 29.1 | |
2026.03 | 26.2 | 8.3 | 21.1 | 22.4 | |
2026.03 | 22.3 | 8.3 | 0 | 15.2 | |
2026.03 | 20.4 | 4.2 | 10.5 | 15.8 | |
2026.03 | 8.7 | 4.2 | 2.6 | 6.7 | |
2026.03 | 7.8 | 0 | 0 | 4.8 | |
2026.03 | 6.8 | 4.2 | 2.6 | 5.4 |