Math on Real-data Math Qwen outputs (3% verified data)
55.1Original Accuracy
Logistic Regression
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.06 | 55.1 | 55.71 | 0.61 | 274 | |
2026.06 | 55.1 | 54.28 | -0.82 | 274 | |
2026.06 | 55.1 | 59.7 | 4.6 | 274 | |
2026.06 | 55.1 | 53.82 | -1.28 | 274 | |
2026.06 | 55.1 | 58.88 | 3.78 | 274 | |
2026.06 | 55.1 | 79.27 | 24.17 | 291.2 |