Faithfulness detection on In-domain Step-level Benchmark Knowledge
83.4FF1
GeoFaith
Updated 7d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 83.4 | 70.3 | |
2026.05 | 81.2 | 72.3 | |
2026.05 | 79.3 | 62.5 | |
2026.05 | 77 | 63.7 | |
2026.05 | 76.1 | 59.8 | |
2026.05 | 75.8 | 52.2 | |
2026.05 | 74.8 | 57.6 | |
2026.05 | 73.5 | 53.2 | |
2026.05 | 69.7 | 42.3 | |
2026.05 | 54.2 | 40.1 |