LLM Routing on BBEH (val)
66.4Top-1 AccORACLE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ORACLEModel Pool=Pool Large, Router Category=Oracle2026.01 | 66.4 | — | |
| ORACLEModel Pool=Pool Small, Router Category=Oracle2026.01 | 56.7 | — | |
| LLMRANKModel Pool=Pool Large, Router Category=Query-answer Routers2026.01 | 37.5 | — | |
| CASCAL-GTModel Pool=Pool Large, Router Category=Query-answer Routers2026.01 | 37.4 | 35.5 | |
| AVENGERSModel Pool=Pool Large, Router Category=Query-answer Routers2026.01 | 36.5 | — | |
| TOP-1 / TOP-3Model Pool=Pool Large, Router Category=Baseline2026.01 | 34 | 34.3 | |
| SMOOTHIEModel Pool=Pool Large, Router Category=Query-only Routers2026.01 | 32 | 32 | |
| CASCALModel Pool=Pool Large, Router Category=Query-only Routers2026.01 | 30.7 | 33 | |
| AVENGERSModel Pool=Pool Small, Router Category=Query-answer Routers2026.01 | 27.3 | — | |
| LLMRANKModel Pool=Pool Small, Router Category=Query-answer Routers2026.01 | 27.2 | — | |
| CASCALModel Pool=Pool Small, Router Category=Query-only Routers2026.01 | 25.4 | 23.5 | |
| TOP-1 / TOP-3Model Pool=Pool Small, Router Category=Baseline2026.01 | 25.1 | 25 | |
| CASCAL-GTModel Pool=Pool Small, Router Category=Query-answer Routers2026.01 | 25 | 26.2 | |
| SMOOTHIEModel Pool=Pool Small, Router Category=Query-only Routers2026.01 | 21.1 | 23.1 |