Multi-document Question Answering on FRAMES (test)
0.8762HypervolumeRADAR
Evaluation Results
| Method | Links | |
|---|---|---|
| RADAREvaluation Protocol=ID (In-distribution)2025.09 | 0.8762 | |
| IRT-RouterEvaluation Protocol=ID (In-distribution)2025.09 | 0.8501 | |
| RouterBenchEvaluation Protocol=ID (In-distribution)2025.09 | 0.8325 | |
| Random-PairEvaluation Protocol=ID (In-distribution)2025.09 | 0.6589 |