Model Routing on OOD Set AIME Humanity's Last Exam SimpleQA OlympiadBench (test)
50.8Avg. A
SCOPE
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 50.8 | 59.32 | 3.08 | |
2026.01 | 48.4 | 53.34 | 1.38 | |
2026.01 | 42 | 34.2 | 1.37 | |
2026.01 | 41.6 | 33 | 3.59 | |
2026.01 | 41.2 | 31.8 | 11.89 | |
2026.01 | 41.2 | 31.8 | 11.52 | |
2026.01 | 40.4 | 29.41 | 11.86 | |
2026.01 | 40.4 | 29.41 | 11.79 | |
2026.01 | 39.6 | 27.02 | 0.75 | |
2026.01 | 38.4 | 23.43 | 0.46 | |
2026.01 | 30.57 | - | 1.16 |