Zero-shot General Evaluation on HellaSwag, MathQA, MMLU, OpenBookQA, WinoGrande, GSM8K, and HumanEval
82.72HellaSwag Accuracy
FP16
Updated 1d ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.05 | 82.72 | 63.85 | 84.53 | 44.2 | 76.8 | 77.18 | 95.73 | 75 | |
2026.05 | 82.17 | 61.34 | 83.49 | 45.2 | 76.09 | 76.19 | 92.68 | 73.88 | |
2026.05 | 82.11 | 61.17 | 83.81 | 45.6 | 77.03 | 76.57 | 92.68 | 74.14 | |
2026.05 | 81.42 | 59.4 | 82.52 | 44.2 | 76.09 | 76.65 | 92.07 | 73.19 | |
2026.05 | 81.35 | 60.03 | 78.77 | 45 | 72.85 | 83.47 | 56.1 | 68.22 | |
2026.05 | 80.93 | 62.78 | 83.94 | 44.8 | 76.4 | 75.97 | 94.51 | 74.19 | |
2026.05 | 79.92 | 54.07 | 75.83 | 43.4 | 72.14 | 79.45 | 38.41 | 63.32 | |
2026.05 | 79.81 | 57.05 | 76.45 | 41.8 | 70.64 | 82.64 | 56.1 | 66.36 | |
2026.05 | 79.55 | 57.62 | 79.97 | 43.8 | 71.35 | 80.82 | 53.05 | 66.59 | |
2026.05 | 79.24 | 60.17 | 76.98 | 44.8 | 74.19 | 85.37 | 50.61 | 67.34 | |
2026.05 | 78.73 | 50.95 | 79.68 | 43.8 | 70.4 | 66.49 | 91.46 | 68.79 | |
2026.05 | 78.69 | 49.75 | 79.76 | 43.8 | 71.74 | 71.49 | 91.46 | 69.53 | |
2026.05 | 78.55 | 49.01 | 75.37 | 44.4 | 71.67 | 79.53 | 43.29 | 63.12 | |
2026.05 | 78.02 | 60.67 | 81.47 | 44.8 | 75.85 | 71.49 | 92.68 | 72.14 | |
2026.05 | 77.7 | 39.03 | 55.6 | 44.4 | 70.88 | 39.12 | 26.83 | 50.51 | |
2026.05 | 76.83 | 36.45 | 53.16 | 44.4 | 70.88 | 32.15 | 21.34 | 47.89 | |
2026.05 | 76.4 | 37.29 | 53.58 | 43 | 70.56 | 34.57 | 20.12 | 47.93 | |
2026.05 | 76.15 | 38.39 | 54.64 | 43.6 | 70.17 | 33.66 | 25 | 48.8 | |
2026.05 | 75.88 | 37.29 | 50.92 | 44.2 | 69.3 | 30.4 | 26.22 | 47.74 | |
2026.05 | 75.06 | 38.16 | 53.59 | 43.2 | 70.88 | 30.33 | 27.44 | 48.38 | |
2026.05 | 74.09 | 52.7 | 70.87 | 43.4 | 72.93 | 75.51 | 43.9 | 61.91 | |
2026.05 | 70.24 | 27.47 | 54.63 | 38.6 | 65.59 | 18.35 | 1.22 | 39.44 | |
2026.05 | 70.16 | 24.89 | 39.17 | 39.4 | 60.62 | 4.32 | 0 | 34.08 | |
2026.05 | 69.96 | 33.37 | 46.41 | 39.2 | 68.82 | 15.47 | 14.02 | 41.04 | |
2026.05 | 69.42 | 30.82 | 41.8 | 37.2 | 65.59 | 11.37 | 8.54 | 37.82 | |
2026.05 | 67.73 | 29.51 | 43.41 | 38.2 | 63.54 | 12.43 | 11.59 | 38.06 | |
2026.05 | 66.44 | 45.09 | 70.02 | 40 | 67.72 | 49.36 | 26.83 | 52.21 | |
2026.05 | 66.25 | 32.19 | 46.29 | 39.6 | 69.85 | 15.85 | 12.8 | 40.4 | |
2026.05 | 63.05 | 33.17 | 48.82 | 36.4 | 60.85 | 22.67 | 11.59 | 39.51 | |
2026.05 | 62.82 | 31.83 | 44.51 | 35.4 | 59.98 | 19.64 | 7.93 | 37.44 | |
2026.05 | 61.44 | 25.09 | 27.72 | 35.8 | 59.98 | 2.96 | 0 | 30.43 |