o1 Preview on MMLU (Massive Multitask Language Understanding): Score Breakdown
o1 Preview × MMLU (Massive Multitask Language Understanding)
Detalhamento de pontuação
| Ranking de modelos | Pontuação |
|---|---|
| #20 / 205 | 85.3 |
Análise de desempenho
o1 Preview achieves 85.3 on MMLU (Massive Multitask Language Understanding).