0

MMLU RL Env (Prime Community)

Fresh

MMLU evaluator for multi-subject multiple-choice reasoning.

Type
RL Env
Publisher
Prime Community
Tags
NLPGeneral Knowledge
Runtime
single-turn
License
unknown
Size
v0.1.0
Published
Apr 2026
Canonical
app.primeintellect.ai/dashboard/environments/prime-community/mmlu

Cite

Notes

Only stored in your browser.

Lift evidence

1
EvalTools known to liftSource paper
Measuring Massive Multitask Language UnderstandingMMLU RL Env (Prime Community)-

Evals this tool implements

2

Same problem set, this tool's harness. Run it to score a model on the test.

Massive Multitask Language Understanding (MMLU)

University of California, Berkeley

57-subject multiple-choice exam testing broad world knowledge and reasoning across academic and professional domains.

SaturatedFactual RecallScientific Reasoning

MMLU: Measuring Massive Multitask Language Understanding

University of California, Berkeley

Evaluate models on 57 tasks including elementary mathematics, US history, computer science, law, and more.

ActiveKnowledge