LLM Routing on MedMCQA
96.3Top-1 AccORACLE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ORACLEModel Pool=Pool Large, Training Data Source=Gemini-2.5-Flash2026.01 | 96.3 | — | |
| TOP-1 / TOP-3Model Pool=Pool Large, Training Data Source=Gemini-2.5-Flash2026.01 | 92.7 | 88.5 | |
| ORACLEModel Pool=Pool Small, Training Data Source=Gemini-2.5-Flash2026.01 | 91.2 | — | |
| AVENGERSModel Pool=Pool Large, Router Category=Query-answer Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 84.8 | — | |
| CASCAL-GTModel Pool=Pool Large, Router Category=Query-answer Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 84.7 | 86 | |
| CASCALModel Pool=Pool Large, Router Category=Query-only Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 83.2 | 85.9 | |
| LLMRANKModel Pool=Pool Large, Router Category=Query-answer Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 81.2 | — | |
| SMOOTHIEModel Pool=Pool Large, Router Category=Query-only Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 77.7 | 80.3 | |
| TOP-1 / TOP-3Model Pool=Pool Small, Training Data Source=Gemini-2.5-Flash2026.01 | 71 | 70.2 | |
| AVENGERSModel Pool=Pool Small, Router Category=Query-answer Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 69.2 | — | |
| CASCAL-GTModel Pool=Pool Small, Router Category=Query-answer Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 68.4 | 68.5 | |
| LLMRANKModel Pool=Pool Small, Router Category=Query-answer Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 67.5 | — | |
| CASCALModel Pool=Pool Small, Router Category=Query-only Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 65.9 | 68 | |
| SMOOTHIEModel Pool=Pool Small, Router Category=Query-only Routers, Training Data Source=Gemini-2.5-Flash2026.01 | 62.9 | 67 |