Zero-shot Natural Language Understanding Suite (ARC, BoolQ, COPA, MMLU, OBQA, PIQA, RTE, Winogrande)
56.14ARC-c
MoNE
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
2025.07 | 56.14 | 79.17 | 89.11 | 85 | 74.04 | 43 | 79.27 | 77.98 | 70.48 | 72.69 | |
2025.07 | 55.89 | 79.42 | 88.69 | 84 | 77.82 | 44.8 | 80.3 | 82.31 | 70.64 | 73.76 | |
2025.07 | 53.75 | 78.32 | 88.53 | 85 | 74.6 | 43 | 79.92 | 79.78 | 69.61 | 72.5 | |
2025.07 | 52.73 | 76.98 | 88.75 | 83 | 72.25 | 44.4 | 79.71 | 80.87 | 70.4 | 72.12 | |
2025.07 | 50.85 | 76.68 | 85.72 | 85 | 69.43 | 42.8 | 77.31 | 81.95 | 70.17 | 71.1 | |
2025.07 | 50 | 72.85 | 86.91 | 91 | 65.02 | 45.4 | 81.12 | 77.62 | 76.09 | 71.78 | |
2025.07 | 49.66 | 69.44 | 86.45 | 93 | 74.06 | 44.2 | 81.23 | 74.73 | 74.27 | 71.89 | |
2025.07 | 49.66 | 68.73 | 86.88 | 94 | 71.64 | 45.2 | 81.07 | 75.45 | 73.09 | 71.75 | |
2025.07 | 49.15 | 69.78 | 84.77 | 87 | 70.99 | 44.8 | 81.34 | 74.37 | 74.19 | 70.71 | |
2025.07 | 46.67 | 66.25 | 86.45 | 88 | 69.46 | 43.4 | 80.2 | 74.73 | 75.14 | 70.03 | |
2025.07 | 44.62 | 68.6 | 80.52 | 77 | 59.75 | 40.4 | 75.3 | 70.4 | 62.51 | 64.34 | |
2025.07 | 29.44 | 54.17 | 59.51 | 70 | 23.92 | 32.8 | 70.02 | 54.87 | 49.57 | 49.37 |