Zero-shot Question Answering on (BoolQ, Winogrande, PIQA, OpenBookQA, HellaSwag, ARC-Easy, ARC-Challenge)
83.76BoolQ Accuracy (Zero-shot)
Dense
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.03 | 83.76 | 77.98 | 82.7 | 48.8 | 83.81 | 81.06 | 57.25 | 73.62 | |
2026.03 | 80.58 | 75.3 | 77.04 | 41.6 | 69.19 | 70.03 | 43.86 | 65.37 | |
2026.03 | 80.55 | 71.98 | 80.52 | 45.2 | 79.36 | 77.53 | 48.98 | 69.16 | |
2026.03 | 80.18 | 75.14 | 76.44 | 42.6 | 69.4 | 70.79 | 43.77 | 65.47 | |
2026.03 | 79.02 | 73.95 | 77.31 | 42.8 | 71.96 | 69.53 | 42.75 | 65.33 | |
2026.03 | 77.68 | 69.14 | 79.05 | 44.2 | 76.01 | 74.54 | 46.33 | 66.71 | |
2026.03 | 75.6 | 73.23 | 75.83 | 40.7 | 68.13 | 69.49 | 41.38 | 63.48 | |
2026.03 | 74.1 | 74.03 | 75.63 | 40 | 64.73 | 69.99 | 40.78 | 62.75 | |
2026.03 | 68.17 | 61.88 | 67.85 | 32.2 | 46.7 | 48.11 | 28.67 | 50.51 | |
2026.03 | 65.9 | 63.22 | 68.01 | 33 | 47.61 | 49.54 | 27.99 | 50.75 | |
2026.03 | 64.86 | 56.2 | 66.92 | 33.6 | 47.17 | 49.45 | 27.22 | 49.35 | |
2026.03 | 64.04 | 59.19 | 62.84 | 30.6 | 41.35 | 41.71 | 25.26 | 46.43 | |
2026.03 | 63.61 | 58.41 | 62.35 | 29.6 | 40.38 | 40.19 | 23.46 | 45.43 | |
2026.03 | 62.42 | 56.04 | 60.39 | 29.2 | 35.27 | 38.01 | 22.61 | 43.42 | |
2026.03 | 62.14 | 55.25 | 63 | 30.4 | 39.24 | 44.15 | 25.94 | 45.73 | |
2026.03 | 62.08 | 50.75 | 57.34 | 28.2 | 31.62 | 35.56 | 21.25 | 40.97 | |
2026.03 | 60.46 | 51.38 | 55.11 | 28.2 | 32.32 | 32.45 | 21.59 | 40.22 | |
2026.03 | 48.5 | 49.33 | 53.86 | 25.8 | 30.21 | 30.64 | 21.33 | 37.1 | |
2026.03 | 39.57 | 57.14 | 67.63 | 35.8 | 57.2 | 54.55 | 34.56 | 49.49 | |
2026.03 | 38.65 | 49.49 | 53.1 | 26.6 | 29.51 | 32.11 | 24.49 | 36.28 | |
2026.03 | 37.95 | 49.25 | 51.52 | 28 | 26.32 | 27.9 | 26.96 | 35.41 |