MMLU: Management

Accuracy on MMLU's management questions, one of 57 subject tests of academic and professional knowledge.

Also known as: management

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryknowledge
SubcategoryOther
Page statusactive
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size103
Dataset licenceMIT
PublisherUC Berkeley

What it measures

Business-management principles at the level of an introductory management or MBA-style course: organisational behaviour, leadership, human resources, strategy, and operations. Framed as four-option multiple-choice questions and scored zero-shot or few-shot by exact match against the labelled option, as one of the 57 subject subsets that make up the MMLU benchmark.

Task format

Four-option multiple-choice question answering (A-D), one correct answer, zero-shot or few-shot.

Models reporting this benchmark

These figures come from the model cards, which carry one collection date per card and no per-score attribution. They are shown as reported, not as verified evidence.
ModelProviderScoreCard as of
Nous Hermes 2 Yi 34BNous Research92.22024-07
Yi 1.5 34B01.AI91.32026-04
Meta Llama 3 70BMeta89.32024-07
Meta Llama 3 70B InstructMeta89.32026-04
Meta Llama 3 70B InstructNous Research89.32026-04
Yi 34B 200K01.AI89.32024-07
Mixtral 8x7B v0.1Mistral AI88.32026-04
Yi 1.5 34B Chat01.AI88.32026-04
Yi 1.5 34B Chat 16K01.AI88.32024-07
Meta Llama 3 8BMeta87.42024-07
Meta Llama 3 8BNous Research87.42024-07
Mixtral 8x22B Instruct v0.1Mistral AI87.42026-04
Yi 34B Chat01.AI87.42024-07
Yi 1.5 34B 32K01.AI86.42024-07
Yi 1.5 9B Chat01.AI86.42024-07
Nous Hermes 2 Mixtral 8x7B DPONous Research85.42024-07
gemma 7B itGoogle DeepMind84.52024-07
Mixtral 8x7B Instruct v0.1Mistral AI84.52026-04
Qwen2 1.5B InstructAlibaba / Qwen Team83.52024-07
Yi 9B01.AI83.52024-07
Phi 3 mini 128K instructMicrosoft82.52024-07
Mistral 7B v0.3Mistral AI81.62024-07
mistral 7B v0.3 bnb 4bitUnsloth81.62024-07
Yi 1.5 9B 32K01.AI81.62024-07
Hermes 2 Pro Llama 3 8BNous Research80.62024-07
Hermes 2 Theta Llama 3 8BNous Research80.62024-07
Nous Hermes 2 SOLAR 10.7BNous Research80.62024-07
Phi 3 mini 4K instructMicrosoft80.62024-07
Yi 1.5 6B Chat01.AI80.62024-07
Yi 1.5 9B01.AI80.62024-07
Yi 6B01.AI80.62024-07
Yi 6B Chat01.AI80.62024-07
Yi 1.5 6B01.AI79.62024-07
falcon 40BTII78.62024-07
Meta Llama 3 8B InstructMeta78.62024-07
Meta Llama 3 8B InstructNous Research78.62024-07
Yi 1.5 9B Chat 16K01.AI76.72024-07
Mistral 7B Instruct v0.2Mistral AI75.72024-07
phi 2Microsoft70.92024-07
deepseek llm 7B baseDeepSeek65.02024-07
deepseek llm 7B chatDeepSeek65.02024-07
Qwen2 0.5B InstructAlibaba / Qwen Team63.12024-07
chatglm2 6BZhipu AI62.12024-07
gemma 2BGoogle DeepMind56.32024-07
gemma 2B itGoogle DeepMind44.72024-07
deepseek coder 6.7B baseDeepSeek42.72024-07
deepseek coder 6.7B instructDeepSeek38.82024-07
deepseek coder 1.3B baseDeepSeek37.92024-07
deepseek coder 1.3B instructDeepSeek37.92024-07
OLMo 1B hfAllen AI22.32024-07

Data

This page as JSON · Edit on GitHub