MMMLU

Benchmark Family
MMMLU
Organization
OpenAI
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedmmmlu/defaultACTIVE3

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-002O47-007 Claude Opus 4.7 MMMLU Overall 91.5% Unknown Primary source ANTHR-O47
BR-00331P-017 Gemini 3.1 Pro MMMLU Overall 92.6% Unknown Primary source GOOGL-G31P
BR-00735-027 Qwen3.5-397B-A17B MMMLU Overall 88.5 Unknown Primary source QWEN-35