Question Answering on SimpleQA 50/50 calibration (test)
26.7CR (%)Diagnostic learned router
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Diagnostic learned router2026.05 | 26.7 | 0.193 | |
| Optimal pair2026.05 | 15.1 | 0.158 | |
| Optimal subsequence2026.05 | 14.2 | 0.156 | |
| Full fixed chain2026.05 | 1.3 | 0.093 | |
| Always-expensive2026.05 | 0 | — |