Knowledge MCQ on Global-MMLU
70.4Accuracystandard cascade
Evaluation results
| Method | Links | |
|---|---|---|
| standard cascadeModel=GPT-4o-mini2026.06 | 70.4 | |
| context-aware cascadeModel=GPT-4o-mini2026.06 | 69.84 | |
| end-to-endModel=GPT-4o-mini2026.06 | 61.9 | |
| context-aware cascadeModel=Llama-3.1-8B-Instruct2026.06 | 43.12 | |
| standard cascadeModel=Llama-3.1-8B-Instruct2026.06 | 40.76 | |
| end-to-endModel=Llama-3.1-8B-Instruct2026.06 | 36.12 | |
| context-aware cascadeModel=Mistral-7B-Instruct-v0.32026.06 | 32.07 | |
| end-to-endModel=Mistral-7B-Instruct-v0.32026.06 | 26.36 | |
| standard cascadeModel=Mistral-7B-Instruct-v0.32026.06 | 26.29 |