Multilingual Reasoning on GlobalMMLU
88.77English Accuracy
Qwen2.5-72B-Instruct
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2025.12 | 88.77 | 3.11 | 85.84 | 3.5 | 78.29 | 7.96 | 81.48 | 4.51 | 82.78 | 3.75 | 81.8 | 9.63 | 87.31 | 3.3 | 81.05 | 6.16 | 83.67 | 4.74 | 82.39 | 6.09 | |
2025.12 | 88.62 | 2.81 | 85.11 | 4.24 | 79.89 | 6.92 | 80.25 | 5.94 | 83.92 | 4.91 | 78.87 | 11.72 | 86.87 | 3.52 | 80.84 | 7.21 | 83.63 | 4.91 | 81.64 | 7.99 | |
2025.12 | 88.12 | 0.91 | 85.88 | 1.71 | 81.13 | 3.23 | 81.48 | 3.15 | 83.78 | 2.38 | 81.06 | 8.5 | 87.02 | 1.31 | 81.91 | 4.13 | 84.3 | 2.2 | 82.57 | 5.11 | |
2025.12 | 87.14 | 2.96 | 83 | 2.64 | 69.96 | 7.8 | 76.86 | 5.77 | 77.38 | 4.46 | 77.01 | 13.3 | 85.15 | 2.81 | 75.42 | 7.44 | 79.93 | 4.58 | 77.22 | 8.17 | |
2025.12 | 87.06 | 2.61 | 84.33 | 3.99 | 81.31 | 6.87 | 78.71 | 6.12 | 83.95 | 3.71 | 80.33 | 12.57 | 85.7 | 3.3 | 81.11 | 7.25 | 82.93 | 4.86 | 82.2 | 8 | |
2025.12 | 86.98 | 2.16 | 83.76 | 2.28 | 78.51 | 4.44 | 79.59 | 4.04 | 80.94 | 2.28 | 78.4 | 9.81 | 85.38 | 2.22 | 79.36 | 5.14 | 82.22 | 3.23 | 79.68 | 6.04 |