Natural Language Inference on MNLI (mismatched)
91Accuracy
METALM
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2022.06 | 91 | - | |
2023.07 | 90.4 | - | |
2023.07 | 90.3 | - | |
2022.06 | 90.2 | - | |
2023.07 | 88.7 | - | |
2022.06 | 87.6 | - | |
2023.07 | 87.5 | - | |
2023.05 | 86.18 | 1.4 | |
2023.05 | 85.24 | 0.46 | |
2023.05 | 84.9 | - | |
2023.05 | 83 | - | |
2023.05 | 82.4 | - | |
2023.05 | 82.4 | - | |
2023.05 | 81.8 | - | |
2023.05 | 81.2 | - | |
2023.05 | 79.79 | 0.06 | |
2023.05 | 78.3 | - | |
2023.05 | 77.22 | -2.07 | |
2023.05 | 76.5 | - | |
2023.05 | 76.42 | 1.41 | |
2023.05 | 76.3 | - | |
2023.05 | 75.6 | - | |
2023.05 | 75.42 | 0.41 | |
2023.05 | 74.1 | - | |
2023.05 | 74 | 0.02 | |
2023.05 | 73.49 | -0.49 | |
2023.05 | 73.36 | 0.84 | |
2023.11 | 73.2 | - | |
2023.11 | 72.6 | - | |
2023.11 | 72.3 | - | |
2023.11 | 72.1 | - | |
2023.06 | 72 | - | |
2023.11 | 71.9 | - | |
2023.06 | 71.8 | - | |
2023.11 | 71.6 | - | |
2023.11 | 71.4 | - | |
2023.07 | 69.7 | - | |
| 69.6 | - | ||
2023.07 | 69.2 | - | |
2023.06 | 69.1 | - | |
2023.07 | 69 | - | |
2023.07 | 68.9 | - | |
2023.07 | 68.6 | - | |
2023.07 | 68.5 | - | |
2023.07 | 68.1 | - | |
2023.11 | 67.3 | - | |
2023.11 | 66.7 | - | |
2023.11 | 66.4 | - | |
2023.11 | 63.3 | - | |
2023.06 | 61.8 | - | |
2023.11 | 61.8 | - | |
2023.11 | 57 | - | |
2022.12 | 56.8 | - | |
2023.07 | 56.16 | - | |
2023.11 | 55.8 | - | |
2023.07 | 53.56 | - | |
2023.05 | 52.81 | -0.1 | |
2022.12 | 51.7 | - | |
2023.06 | 50.6 | - | |
2023.05 | 49.24 | 1.67 | |
2023.06 | 47.8 | - | |
2023.06 | 46.1 | - | |
2023.07 | 44.03 | - | |
2023.05 | 43.66 | -3.91 | |
2023.07 | 42.92 | - | |
2023.07 | 38.75 | - | |
2023.07 | 36.28 | - | |
2023.06 | 33.3 | - |