o1 Preview on MMLU (Massive Multitask Language Understanding): Score Breakdown

o1 Preview × MMLU (Massive Multitask Language Understanding)

Ergebnisaufschlüsselung

Modell-RankingErgebnis
#20 / 20585.3

Leistungsanalyse

o1 Preview achieves 85.3 on MMLU (Massive Multitask Language Understanding).