Language Modeling Evaluation on MMLU, GSM8k, HellaSwag, WinoGrande
72.98MMLU Accuracy
FP16
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2025.09 | 72.98 | 90.9 | 75.52 | 70.56 | 77.49 | - | |
2025.09 | 71.34 | 89.23 | 75.24 | 70.4 | 76.55 | 98.79 | |
2025.09 | 71.06 | 88.32 | 74.58 | 68.03 | 75.5 | 97.43 | |
2025.09 | 70.94 | 89.08 | 74.67 | 68.51 | 75.8 | 97.82 | |
2025.09 | 70.9 | 88.17 | 75.01 | 70.09 | 76.04 | 98.13 | |
2025.09 | 70.78 | 90.3 | 74.63 | 70.72 | 76.61 | 98.86 | |
2025.09 | 70.45 | 87.41 | 74.25 | 68.9 | 75.25 | 97.11 | |
2025.09 | 70.35 | 89.61 | 74.61 | 70.56 | 76.28 | 98.44 | |
2025.09 | 70.19 | 86.35 | 73.02 | 68.11 | 74.42 | 96.04 | |
2025.09 | 69.53 | 86.43 | 73.55 | 65.75 | 73.82 | 95.26 | |
2025.09 | 69.45 | 87.34 | 74.03 | 69.85 | 75.17 | 97 | |
2025.09 | 69.13 | 84.84 | 73.17 | 68.03 | 73.79 | 95.23 | |
2025.09 | 69.09 | 86.66 | 73.47 | 67.96 | 74.3 | 95.88 | |
2025.09 | 68.01 | 84.23 | 71.65 | 67.8 | 72.92 | 94.11 | |
2025.09 | 67.69 | 84.23 | 71.24 | 67.4 | 72.64 | 93.74 | |
2025.09 | 67.57 | 83.78 | 71.32 | 67.32 | 72.5 | 93.56 | |
2025.09 | 67.27 | 81.58 | 71.41 | 66.38 | 71.66 | 92.48 |