Long-form Factual Generation on LongFact
84.2Fact Recall (FR) - Science
ArbGraph
Updated 3mo ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
2026.04 | 84.2 | 85.1 | 86.1 | 85.3 | 84 | 83 | 85.9 | 84.7 | 84.9 | |
2026.04 | 83.8 | 81.6 | 84 | 82.5 | 80.5 | 81.9 | 77.1 | 81.9 | 81.7 | |
2026.04 | 83.5 | 84.4 | 86.2 | 83.3 | 82.5 | 79.8 | 84.7 | 81.6 | 83.3 | |
2026.04 | 80.4 | 77.4 | 85.2 | 75.8 | 82.4 | 79.2 | 76.3 | 77.9 | 79.2 | |
2026.04 | 79.7 | 76.6 | 82.8 | 77.1 | 80.2 | 79.1 | 74 | 81.2 | 78.8 | |
2026.04 | 79.2 | 78.4 | 80.5 | 77.1 | 76.2 | 75.1 | 78.2 | 73.6 | 78.3 | |
2026.04 | 78.4 | 79.7 | 82.4 | 73.3 | 76.6 | 75.2 | 69.3 | 75.4 | 76.3 | |
2026.04 | 78.2 | 69.2 | 78.1 | 71.3 | 70.1 | 74.3 | 69.2 | 75.2 | 73.3 | |
2026.04 | 69.5 | 69.2 | 71.9 | 68.7 | 67.3 | 68.3 | 66.8 | 70.4 | 69 | |
2026.04 | 69.1 | 56.1 | 68.3 | 61.9 | 66.6 | 69 | 73.4 | 60.8 | 64.7 | |
2026.04 | 65.7 | 70 | 65.6 | 62.5 | 55.2 | 58.5 | 55.8 | 69.4 | 63.1 | |
2026.04 | 65.6 | 59.2 | 71.3 | 62.4 | 64.4 | 66 | 50.6 | 70.8 | 63.3 | |
2026.04 | 64.9 | 73.7 | 64.7 | 61.6 | 58.5 | 56.7 | 56.6 | 68.6 | 63.5 | |
2026.04 | 59.6 | 68.8 | 69.8 | 66 | 62.2 | 59.5 | 57.7 | 72.1 | 64.6 |