Mathematical Reasoning on MATH-500 (unsat.)
77.3Best Single Router PerformanceGap decomposition method
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Gap decomposition methodNested bootstrap k=30, Temperature T=0.2, N=500, Model pool size=112026.07 | 77.3 | 87.3 | 83.7 | 10 | 6.4 | 3.6 | 36 | 28 | 43 | 2.1 | |
| Best-single routerTemperature T=0.2, Model pool size=112026.07 | 77.3 | — | — | — | — | — | — | — | — | — |