Reasoning on Overall
73.9Overall Accuracy
GeoFaith
Updated 7d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 73.9 | 1,300 | 82.3 | |
2026.05 | 69.9 | 1,600 | 75.8 | |
2026.05 | 69.8 | 1,400 | 72.4 | |
2026.05 | 69.6 | 1,900 | 74.1 | |
2026.05 | 66.8 | 900 | 68.5 | |
2026.05 | 66 | 3,200 | 79.2 | |
2026.05 | 51.8 | 700 | 52.1 | |
2026.05 | 46.9 | 800 | 49.9 | |
2026.05 | 40.4 | 600 | 41.1 | |
2026.05 | 39.3 | 300 | 33 | |
2026.05 | 36.4 | 500 | 25.1 | |
2026.05 | 32.4 | 1,100 | 43.3 |