o1 Preview on MMLU (Massive Multitask Language Understanding): Score Breakdown
o1 Preview × MMLU (Massive Multitask Language Understanding)
Dettaglio punteggi
| Classifica modelli | Punteggio |
|---|---|
| #20 / 205 | 85.3 |
Analisi delle prestazioni
o1 Preview achieves 85.3 on MMLU (Massive Multitask Language Understanding).