Benchmark family

MMLU

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 2 definitions is resolved separately.

General reasoningKnowledge

Definitions

Compare versions →

Newest first, following the recorded successor chain. Each definition is resolved against models separately.

BenchmarkMMLU
ActiveNewest in family
Scale
57 tasks
Primary metric
Accuracy
Applicable models
30
BenchmarkMMLU-Pro
Active
Derived from MMLU
Scale
12,032 questions
Primary metric
Accuracy
Applicable models
13

Family methodology

No family-level methodology recorded.

Across definitions

Tasks: Ten-option academic question answering, Multiple-choice academic/professional question answering
Sources: None recorded at family level
Last reviewed: 2026-09-22

Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.