Natural Language Understanding on GLUE (Subset: CoLA, QNLI, QQP, RTE, SST-2, STS-B)
97.99SST-2 Accuracy
MSRS
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2025.08 | 97.99 | 0.64 | 80.97 | 82.89 | 65.01 | 69.12 | 75.78 | |
2025.08 | 96.41 | 0.5743 | 75.71 | 83.17 | 63.36 | 67.01 | 73.84 | |
2025.08 | 96.01 | 0.6342 | 80.7 | 83.17 | 63.36 | 67.01 | 77.01 | |
2025.08 | 95.85 | 0.6662 | 80.18 | 81.85 | 63.85 | 65.77 | 75.69 | |
2025.08 | 94.71 | 0.5266 | 72.08 | 82.79 | 64.26 | 68.97 | 72.57 | |
2025.08 | 92.31 | 0.7821 | 82.28 | 75 | 81.57 | 86.02 | 82.56 | |
2025.08 | 88.5 | 0.7311 | 86.75 | 82.1 | 86.72 | 85.77 | 83.22 | |
2025.08 | 87.5 | 0.7404 | 86.37 | 79.31 | 82.27 | 84.98 | 83 | |
2025.08 | 86.71 | 0.8357 | 32.25 | 81.06 | 77.27 | 32.25 | 65.51 | |
2025.08 | 86.25 | 0.8313 | 49.41 | 77.31 | 76.95 | 35.48 | 68.08 | |
2025.08 | 83.72 | 0.7972 | 57.12 | 84.52 | 61.02 | 61.53 | 70.66 | |
2025.08 | 82.49 | 0.7524 | 54.01 | 82.08 | 63.98 | 54.13 | 69.27 |