MMLU: Marketing

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

Also known as: marketing

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 size234
Dataset licenceMIT
PublisherUC Berkeley

What it measures

Marketing principles at the level of an introductory business course: the marketing mix, branding, market segmentation, consumer behaviour, and promotion strategy. 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
Yi 1.5 34B 32K01.AI95.32024-07
Yi 1.5 34B01.AI94.92026-04
Yi 34B 200K01.AI94.02024-07
Meta Llama 3 70BMeta93.62024-07
Meta Llama 3 70B InstructMeta93.62026-04
Meta Llama 3 70B InstructNous Research93.62026-04
Mixtral 8x22B Instruct v0.1Mistral AI92.72026-04
Mixtral 8x7B Instruct v0.1Mistral AI92.32026-04
Yi 1.5 34B Chat01.AI92.32026-04
Yi 1.5 34B Chat 16K01.AI92.32024-07
Mixtral 8x7B v0.1Mistral AI91.92026-04
Nous Hermes 2 Yi 34BNous Research91.92024-07
Yi 1.5 9B Chat01.AI91.92024-07
Yi 1.5 9B Chat 16K01.AI91.52024-07
Yi 34B Chat01.AI91.52024-07
Yi 9B01.AI91.02024-07
Meta Llama 3 8B InstructMeta90.62024-07
Meta Llama 3 8B InstructNous Research90.62024-07
Nous Hermes 2 Mixtral 8x7B DPONous Research90.22024-07
Phi 3 mini 4K instructMicrosoft90.22024-07
Yi 1.5 6B01.AI90.22024-07
Yi 6B01.AI90.22024-07
Yi 6B Chat01.AI90.22024-07
gemma 7B itGoogle DeepMind89.72024-07
Meta Llama 3 8BMeta89.72024-07
Meta Llama 3 8BNous Research89.72024-07
Yi 1.5 9B01.AI89.72024-07
Yi 1.5 9B 32K01.AI89.72024-07
Hermes 2 Theta Llama 3 8BNous Research89.32024-07
Phi 3 mini 128K instructMicrosoft88.92024-07
Yi 1.5 6B Chat01.AI88.92024-07
Mistral 7B v0.3Mistral AI88.02024-07
mistral 7B v0.3 bnb 4bitUnsloth88.02024-07
Nous Hermes 2 SOLAR 10.7BNous Research88.02024-07
Hermes 2 Pro Llama 3 8BNous Research87.62024-07
Mistral 7B Instruct v0.2Mistral AI86.32024-07
phi 2Microsoft82.52024-07
deepseek llm 7B baseDeepSeek82.12024-07
deepseek llm 7B chatDeepSeek82.12024-07
Qwen2 1.5B InstructAlibaba / Qwen Team80.32024-07
falcon 40BTII79.12024-07
chatglm2 6BZhipu AI69.22024-07
Qwen2 0.5B InstructAlibaba / Qwen Team68.42024-07
deepseek coder 6.7B instructDeepSeek65.42024-07
deepseek coder 6.7B baseDeepSeek63.72024-07
gemma 2BGoogle DeepMind60.72024-07
gemma 2B itGoogle DeepMind59.42024-07
deepseek coder 1.3B baseDeepSeek33.32024-07
deepseek coder 1.3B instructDeepSeek33.32024-07
OLMo 1B hfAllen AI25.22024-07

Data

This page as JSON · Edit on GitHub