Reasoning on GPQA-Diamond, AIME2024, MATH500, and HumanEval
85.77Average Score
Vanilla
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.10 | 85.77 | 65.66 | 81.67 | 97.6 | 98.17 | |
2025.10 | 84.91 | 62.38 | 82.08 | 97.6 | 97.56 | |
2025.10 | 83.6 | 63.14 | 77.92 | 97.6 | 95.73 | |
2025.10 | 83.57 | 61.62 | 77.08 | 97.4 | 98.17 | |
2025.10 | 83.34 | 62.12 | 77.92 | 97 | 96.34 | |
2025.10 | 83.21 | 60.36 | 78.75 | 97.4 | 96.34 | |
2025.10 | 81.28 | 57.33 | 77.5 | 97.6 | 92.68 | |
2025.10 | 80.78 | 54.3 | 77.5 | 97.4 | 93.9 | |
2025.10 | 79.89 | 56.82 | 76.25 | 92.6 | 93.9 | |
2025.10 | 79.63 | 56.32 | 76.25 | 88.4 | 97.56 | |
2025.10 | 79.57 | 57.33 | 71.25 | 96.4 | 93.29 | |
2025.10 | 77.99 | 57.58 | 71.25 | 87.4 | 95.73 | |
2025.10 | 77.59 | 55.56 | 67.92 | 94.8 | 92.07 | |
2025.10 | 77.19 | 54.3 | 71.7 | 86.4 | 96.34 | |
2025.10 | 76.95 | 54.55 | 72.92 | 85.2 | 95.12 | |
2025.10 | 75.99 | 52.28 | 66.25 | 95.2 | 90.24 | |
2025.10 | 75.17 | 49 | 76.7 | 88.4 | 86.58 | |
2025.10 | 75 | 54.3 | 71.7 | 86.8 | 87.2 | |
2025.10 | 73.85 | 57.78 | 70.42 | 78.8 | 88.41 | |
2025.10 | 73.48 | 41.9 | 70.58 | 90 | 91.46 | |
2025.10 | 72.65 | 62.38 | 70.25 | 60.4 | 97.56 |