Ranking Method Evaluation on AIME '25
0.934Mean Kendall's tau_b CorrelationOther Ranking Methods
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Other Ranking MethodsNumber of trials=802026.03 | 0.934 | 0.947 | 0.771 | 19 | 29 |
Loading the SOTA2 catalog…
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Other Ranking MethodsNumber of trials=802026.03 | 0.934 | 0.947 | 0.771 | 19 | 29 |