MMLU: Measuring Massive Multitask Language Understanding Benchmark

Explore score history ↗

MMLU: Measuring Massive Multitask Language Understanding is an AI benchmark in the Benchmark Radar catalog.

Released: 2020-09-08
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

MMLU: Measuring Massive Multitask Language Understanding results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude-Opus-4-1-20250805	—	93.4	—	evidence
Claude-Opus-4-20250514	—	92.8	—	evidence
Gemini-2.5-Pro-Preview-06-05	—	92.4	—	evidence
Gpt-5-2025-08-07	—	93.5	—	evidence
O3-2025-04-16	—	92.3	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite MMLU: Measuring Massive Multitask Language Understanding?

MMLU: Measuring Massive Multitask Language Understanding