Mathematical Reasoning on Math500 (Throughput, Speedup)
3,636.1Throughput
SpecBundle
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.03 | 3,636.1 | 1.48 | |
2026.03 | 2,110.3 | 3.76 | |
2026.03 | 1,685.6 | 2.21 | |
2026.03 | 1,524.9 | 2.69 | |
| 1,479 | 2.63 | ||
2026.03 | 1,469 | 1 | |
2026.03 | 1,399.2 | 2.38 | |
| 1,122.2 | 1.98 | ||
2026.03 | 1,022.7 | 2.08 | |
| 821.8 | 1.39 | ||
2026.03 | 762.7 | 1 | |
2026.03 | 638 | 3.34 | |
2026.03 | 587.4 | 1 | |
2026.03 | 567.4 | 1 | |
2026.03 | 561.8 | 1 | |
2026.03 | 492.1 | 1 | |
| 422.4 | 2.21 | ||
2026.03 | 191 | 1 |