MMLU (uncertainty-routed CoT@8)
General QA · 2023-12-19
MMLU test-split accuracy with Google's uncertainty-routed chain of thought using 8 samples: the majority answer is used when consensus exceeds a threshold tuned on the validation split, and otherwise the greedy answer without chain of thought. Kept separate from single-sample MMLU.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 1.0 Pro | 79.1 |