Benchmark

OpenAI MMLU

MMLU (Massive Multitask Language Understanding) is a comprehensive benchmark that measures a text model's multitask accuracy across 57 diverse academic…

Modality
text
Categories
legal, math, physics, psychology, reasoning, finance, general, healthcare, chemistry, economics
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemma 3n E2B InstructedGoogle0.2232025-06-26evidence
Gemma 3n E4B InstructedGoogle0.3562025-06-26evidence

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.