General Reasoning on MMLU (Accuracy and Token Cost)
81.5Accuracy
Denser
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 81.5 | -58.7 | |
2025.12 | 80.4 | 142.8 | |
2025.12 | 80.1 | 156.3 | |
2025.12 | 79.5 | 127.6 | |
2025.12 | 79.4 | -53.5 | |
2025.12 | 79.1 | 187.2 | |
2025.12 | 78.5 | 289.4 | |
2025.12 | 78.2 | 345.7 | |
2025.12 | 77.3 | 0 | |
2025.12 | 76.4 | -54.2 | |
2025.12 | 75.9 | -50.8 | |
2026.02 | 70.41 | - | |
2026.02 | 63.3 | - | |
2026.02 | 24.48 | - | |
2026.02 | 4.29 | - |