o1 Preview on MMLU (Massive Multitask Language Understanding): Score Breakdown
o1 Preview × MMLU (Massive Multitask Language Understanding)
점수 내역
| 모델 순위 | 점수 |
|---|---|
| #20 / 205 | 85.3 |
성능 분석
o1 Preview achieves 85.3 on MMLU (Massive Multitask Language Understanding).