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

o1 × MMLU (Massive Multitask Language Understanding)

Ergebnisaufschlüsselung

Modell-RankingErgebnis
#13 / 20586.3

Leistungsanalyse

o1 achieves 86.3 on MMLU (Massive Multitask Language Understanding).