Faithfulness Evaluation on Multi-News (test)
38.5SummaC
GPT-5
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 38.5 | 50.65 | |
2025.12 | 37.31 | 43.38 | |
2025.12 | 37.08 | 49.02 | |
2025.12 | 37.07 | 39.78 | |
2025.12 | 36.96 | 18.87 | |
2025.12 | 36.05 | 38.2 | |
2025.12 | 35.86 | 40.98 | |
2025.12 | 35.39 | 40.53 | |
2025.12 | 34.79 | 40.57 | |
2025.12 | 34.12 | 37.48 | |
2025.12 | 33.68 | 37.27 | |
2025.12 | 33.01 | 41.17 |