Mathematical Reasoning on AIME (test)
0.7766HypervolumeIRT-Router
Evaluation Results
| Method | Links | |
|---|---|---|
| IRT-RouterEvaluation Protocol=ID (In-distribution)2025.09 | 0.7766 | |
| RADAREvaluation Protocol=ID (In-distribution)2025.09 | 0.776 | |
| RouterBenchEvaluation Protocol=ID (In-distribution)2025.09 | 0.768 | |
| Random-PairEvaluation Protocol=ID (In-distribution)2025.09 | 0.5159 |