General AI Assistant Tasks on GAIA Level 2 original (test)
59.3Perf (%)
EvoRoute
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 59.3 | 33.6 | 18.3 | |
2026.01 | 58.14 | 192.64 | 25.35 | |
2026.01 | 53.73 | 6.2 | 4.8 | |
2026.01 | 49.74 | 77.4 | 28.15 | |
2026.01 | 49.73 | 35.26 | 10.87 | |
2026.01 | 47.65 | 80.24 | 30.93 | |
2026.01 | 46.23 | 72.1 | 28.9 | |
2026.01 | 46.23 | 41.6 | 14.5 | |
2026.01 | 42.07 | 8.5 | 3.7 | |
2026.01 | 40.92 | 8.9 | 3.8 | |
2026.01 | 39.78 | 8 | 3.5 | |
2026.01 | 39.22 | 43.86 | 21.5 | |
2026.01 | 36.3 | 8.9 | 2.6 | |
2026.01 | 10.34 | 2.58 | 14.9 | |
2026.01 | 4.73 | 0.42 | 1.2 |