MMLU: Abstract Algebra

MMLU subject subset: Undergraduate pure mathematics: group theory, rings, fields and other abstract algebraic structures.

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
Subcategorymath
Page statusactive
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size100
Dataset licenceMIT
PublisherUC Berkeley (original); Center for AI Safety (current host)

What it measures

Undergraduate pure mathematics: group theory, rings, fields and other abstract algebraic structures. Questions are four-option multiple-choice, drawn from the MMLU test set's "math" subcategory within the benchmark's "STEM" top-level group, and are graded on the single correct labelled option.

Task format

Four-option multiple-choice questions, graded on the single correct labelled option; commonly evaluated 5-shot, consistent with the rest of MMLU.

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 Chat01.AI58.02026-04
Yi 1.5 34B Chat 16K01.AI58.02024-07
Yi 1.5 34B 32K01.AI56.02024-07
Yi 1.5 34B01.AI55.02026-04
Mixtral 8x22B Instruct v0.1Mistral AI54.02026-04
Meta Llama 3 70BMeta51.02024-07
Meta Llama 3 70B InstructMeta51.02026-04
Meta Llama 3 70B InstructNous Research51.02026-04
Nous Hermes 2 Yi 34BNous Research49.02024-07
Yi 1.5 9B 32K01.AI48.02024-07
Yi 1.5 9B Chat01.AI46.02024-07
Yi 1.5 9B Chat 16K01.AI46.02024-07
Yi 1.5 6B Chat01.AI45.02024-07
Yi 34B Chat01.AI45.02024-07
Yi 1.5 9B01.AI44.02024-07
Nous Hermes 2 Mixtral 8x7B DPONous Research43.02024-07
Mixtral 8x7B Instruct v0.1Mistral AI42.02026-04
Yi 34B 200K01.AI42.02024-07
Hermes 2 Theta Llama 3 8BNous Research38.02024-07
Phi 3 mini 128K instructMicrosoft38.02024-07
Yi 1.5 6B01.AI37.02024-07
Hermes 2 Pro Llama 3 8BNous Research36.02024-07
Phi 3 mini 4K instructMicrosoft36.02024-07
Meta Llama 3 8BMeta35.02024-07
Meta Llama 3 8BNous Research35.02024-07
Nous Hermes 2 SOLAR 10.7BNous Research35.02024-07
falcon 40BTII34.02024-07
Mixtral 8x7B v0.1Mistral AI34.02026-04
Qwen2 0.5B InstructAlibaba / Qwen Team34.02024-07
Qwen2 1.5B InstructAlibaba / Qwen Team34.02024-07
Yi 9B01.AI34.02024-07
deepseek coder 6.7B baseDeepSeek33.02024-07
deepseek coder 6.7B instructDeepSeek33.02024-07
Meta Llama 3 8B InstructMeta32.02024-07
Meta Llama 3 8B InstructNous Research32.02024-07
Mistral 7B Instruct v0.2Mistral AI32.02024-07
gemma 7B itGoogle DeepMind31.02024-07
Mistral 7B v0.3Mistral AI30.02024-07
mistral 7B v0.3 bnb 4bitUnsloth30.02024-07
Yi 6B01.AI30.02024-07
Yi 6B Chat01.AI30.02024-07
OLMo 1B hfAllen AI29.02024-07
phi 2Microsoft29.02024-07
chatglm2 6BZhipu AI28.02024-07
deepseek coder 1.3B baseDeepSeek28.02024-07
deepseek coder 1.3B instructDeepSeek28.02024-07
gemma 2B itGoogle DeepMind28.02024-07
gemma 2BGoogle DeepMind26.02024-07
deepseek llm 7B baseDeepSeek25.02024-07
deepseek llm 7B chatDeepSeek25.02024-07

Data

This page as JSON · Edit on GitHub