MMLU Benchmark Results & Scores | Benchmark Registry

Versions of Massive Multitask Language Understanding
Version	Released	Models	Results
MMLULatest	September 7, 2020	3	5

Latest version: MMLU

Recently reported results for MMLU
Model	Score	Source
gpt-oss-120b (low)	85.9%	deploymentsafety.openai.com for gpt-oss-120b (low) on Massive Multitask Language Understanding MMLU (opens in a new tab)MMLU AccuracyReported August 5, 2025Model cardOpenAISelf-reportedRecord for gpt-oss-120b on Massive Multitask Language Understanding MMLU
gpt-oss-120b (high)	90.0%	deploymentsafety.openai.com for gpt-oss-120b (high) on Massive Multitask Language Understanding MMLU (opens in a new tab)MMLU AccuracyReported August 5, 2025Model cardOpenAISelf-reportedRecord for gpt-oss-120b on Massive Multitask Language Understanding MMLU
gpt-oss-120b (medium)	88.0%	deploymentsafety.openai.com for gpt-oss-120b (medium) on Massive Multitask Language Understanding MMLU (opens in a new tab)MMLU AccuracyReported August 5, 2025Model cardOpenAISelf-reportedRecord for gpt-oss-120b on Massive Multitask Language Understanding MMLU
GPT-4.5 Preview	90.8%	openai.com for GPT-4.5 Preview on Massive Multitask Language Understanding MMLU (opens in a new tab)MMLU AccuracyReported April 14, 2025Launch postOpenAISelf-reportedRecord for GPT-4.5 Preview on Massive Multitask Language Understanding MMLU
GPT-4.1	90.2%	openai.com for GPT-4.1 on Massive Multitask Language Understanding MMLU (opens in a new tab)MMLU AccuracyReported April 14, 2025Launch postOpenAISelf-reportedRecord for GPT-4.1 on Massive Multitask Language Understanding MMLU