Mathematical Reasoning on Countdown, GSM8K, MATH500, and SVAMP
54.92Accuracy
DiSE-flexible
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 54.92 | |
2026.03 | 53.79 | |
2026.03 | 53.52 | |
2026.03 | 53.37 | |
2026.03 | 52.38 | |
2026.03 | 52.24 |
DiSE-flexible
| Method | Links | |
|---|---|---|
2026.03 | 54.92 | |
2026.03 | 53.79 | |
2026.03 | 53.52 | |
2026.03 | 53.37 | |
2026.03 | 52.38 | |
2026.03 | 52.24 |