Mathematical Reasoning on GSM8K 20 (test)
1.39Speedup (x)
SWIFT
Updated 5mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 1.39 | 98 | |
2026.02 | 1.37 | 95 | |
2026.02 | 1.36 | 95 | |
2026.02 | 1.35 | - | |
2026.02 | 1.31 | 98 | |
2026.02 | 1.31 | - | |
2026.02 | 1.29 | - | |
2026.02 | 1.27 | 92 | |
2026.02 | 1.25 | 92 | |
2026.02 | 1 | - | |
2026.02 | 1 | - | |
2026.02 | 1 | - | |
2026.02 | 0.99 | - | |
2026.02 | 0.97 | - | |
2026.02 | 0.97 | - |