Commonsense Reasoning on StoryCloze
97.6Accuracy
Traditional MTL
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2024.05 | 97.6 | - | |
2024.05 | 95.3 | - | |
2024.05 | 94.9 | - | |
2024.05 | 94.1 | - | |
2024.05 | 93.6 | - | |
2024.05 | 92.5 | - | |
2024.05 | 92.5 | - | |
2024.05 | 91.1 | - | |
2024.05 | 90.3 | - | |
2023.05 | 87.4 | - | |
2023.05 | 86.7 | - | |
2023.05 | 86.1 | - | |
2023.05 | 85.6 | - | |
2025.10 | 84.9 | -2 | |
2023.03 | 84.7 | - | |
2025.10 | 82.7 | 0.2 | |
2023.03 | 81.83 | - | |
2025.10 | 81.6 | 17.2 | |
2024.05 | 81.5 | - | |
2025.10 | 81.1 | -0.2 | |
2025.10 | 80.9 | 7.4 | |
2023.03 | 80.87 | - | |
2025.10 | 80.5 | 4.5 | |
2023.03 | 80.28 | - | |
2023.03 | 78.3 | - | |
2026.02 | 67.72 | - | |
2026.02 | 67.34 | - | |
2026.02 | 67.13 | - | |
2026.02 | 67.13 | - | |
2026.02 | 66.86 | - | |
2026.02 | 66.76 | - | |
2026.02 | 66.7 | - | |
2026.02 | 66.38 | - | |
2026.02 | 65.79 | - |