Math Reasoning on Average (MATH, GSM8K, AIME 2025)
0.92Task Accuracy
GPT-OSS-20B
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 0.92 | 0.64 | 0.58 | 0.46 | |
2026.02 | 0.914 | 0.7 | 0.63 | 0.55 | |
2026.02 | 0.866 | 0.78 | 0.68 | 0.62 | |
2026.02 | 0.827 | 0.8 | 0.72 | 0.66 | |
2026.02 | 0.809 | 0.79 | 0.68 | 0.67 | |
2026.02 | 0.763 | 0.76 | 0.63 | 0.66 | |
2026.02 | 0.724 | 0.84 | 0.64 | 0.61 | |
2026.02 | 0.583 | 0.85 | 0.65 | 0.69 | |
2026.02 | 0.525 | 0.68 | 0.63 | 0.73 |