Multi-domain reasoning on MMLU-Pro
88.7Math Accuracy
SCVC
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.03 | 88.7 | - | 77.9 | 81.7 | 86.2 | 78.7 | 83.8 | 78.7 | 87.3 | 78.6 | 68.1 | 86.1 | 71.6 | 78.2 | 79.7 | - | |
2026.03 | 87.9 | - | 77.4 | 81 | 85.6 | 77.9 | 83.3 | 78.1 | 87 | 77.7 | 67.4 | 85.6 | 70.9 | 77.8 | 79.1 | - | |
2026.03 | 85.5 | - | 76.2 | 79.4 | 83.7 | 75.9 | 82.3 | 77.4 | 86.5 | 75.5 | 65.4 | 84.3 | 69.3 | 76.9 | 77.8 | - | |
2026.03 | 84.9 | - | 74.3 | 77.1 | 83 | 74.1 | 78.6 | 76 | 83 | 73.7 | 59.4 | 83.2 | 67.5 | 75.9 | 75.7 | - | |
2026.03 | 84.5 | - | 73.8 | 76.6 | 82.6 | 73.7 | 78.3 | 75.7 | 82.5 | 72.9 | 59.6 | 83 | 67.3 | 75.5 | 75.3 | - | |
2026.03 | 81.1 | - | 71.9 | 74.5 | 80.2 | 71.8 | 76.1 | 74.2 | 80.9 | 70.4 | 58.5 | 81.2 | 65.4 | 73.7 | 73.2 | - | |
2026.03 | 78.7 | - | 69.9 | 72.4 | 78 | 69.7 | 74.6 | 72 | 79.2 | 68.1 | 57.4 | 79.2 | 63.6 | 71.7 | 71.3 | - | |
2026.03 | 77.6 | - | 71.8 | 74.5 | 78.1 | 72.6 | 79.4 | 68.8 | 83.5 | 72.5 | 66.8 | 76.3 | 66.6 | 71.7 | 73.9 | - | |
2026.03 | 74.1 | - | 69.5 | 71.7 | 75.3 | 70 | 77 | 66.7 | 81.9 | 70 | 65.5 | 73.7 | 64.8 | 69.9 | 71.7 | - | |
2026.03 | 66.1 | - | 63.4 | 64.8 | 67.4 | 63.2 | 70.6 | 62.3 | 74.6 | 63.3 | 61.4 | 66.3 | 60 | 63.5 | 65.2 | - |