Open-ended Factual QA on MKQA
27.92chrFcontext-aware cascade
Evaluation Results
| Method | Links | |
|---|---|---|
| context-aware cascadeModel=GPT-4o-mini2026.06 | 27.92 | |
| standard cascadeModel=GPT-4o-mini2026.06 | 26.25 | |
| end-to-endModel=GPT-4o-mini2026.06 | 23.03 | |
| context-aware cascadeModel=Llama-3.1-8B-Instruct2026.06 | 14.62 | |
| standard cascadeModel=Llama-3.1-8B-Instruct2026.06 | 13.36 | |
| context-aware cascadeModel=Mistral-7B-Instruct-v0.32026.06 | 12.09 | |
| end-to-endModel=Llama-3.1-8B-Instruct2026.06 | 11.51 | |
| standard cascadeModel=Mistral-7B-Instruct-v0.32026.06 | 11.29 | |
| end-to-endModel=Mistral-7B-Instruct-v0.32026.06 | 10.17 |