MMLU: High School European History

MMLU subject subset: European history from a standard high-school or AP-level course.

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
Subcategoryhistory
Page statusactive
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size165
Dataset licenceMIT
PublisherUC Berkeley (original); Center for AI Safety (current host)

What it measures

European history from a standard high-school or AP-level course. Questions are four-option multiple-choice, drawn from the MMLU test set's "history" subcategory within the benchmark's "humanities" 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 32K01.AI88.52024-07
Nous Hermes 2 Yi 34BNous Research87.92024-07
Yi 1.5 34B01.AI87.32026-04
Meta Llama 3 70BMeta86.72024-07
Meta Llama 3 70B InstructMeta86.72026-04
Meta Llama 3 70B InstructNous Research86.72026-04
Yi 1.5 34B Chat01.AI86.12026-04
Yi 1.5 34B Chat 16K01.AI86.12024-07
Mixtral 8x22B Instruct v0.1Mistral AI85.52026-04
Yi 34B Chat01.AI85.52024-07
Yi 34B 200K01.AI84.82024-07
Yi 1.5 9B Chat01.AI84.22024-07
Yi 1.5 9B Chat 16K01.AI83.62024-07
Nous Hermes 2 SOLAR 10.7BNous Research83.02024-07
Yi 1.5 9B01.AI83.02024-07
Yi 1.5 9B 32K01.AI82.42024-07
Mixtral 8x7B v0.1Mistral AI81.82026-04
Phi 3 mini 128K instructMicrosoft81.22024-07
Phi 3 mini 4K instructMicrosoft80.62024-07
Mixtral 8x7B Instruct v0.1Mistral AI80.02026-04
Yi 1.5 6B01.AI79.42024-07
Yi 1.5 6B Chat01.AI78.82024-07
Nous Hermes 2 Mixtral 8x7B DPONous Research78.22024-07
Yi 9B01.AI78.22024-07
Meta Llama 3 8BMeta77.02024-07
Meta Llama 3 8BNous Research77.02024-07
gemma 7B itGoogle DeepMind76.42024-07
Mistral 7B v0.3Mistral AI76.42024-07
mistral 7B v0.3 bnb 4bitUnsloth76.42024-07
Hermes 2 Theta Llama 3 8BNous Research75.82024-07
Yi 6B01.AI75.22024-07
Yi 6B Chat01.AI75.22024-07
Hermes 2 Pro Llama 3 8BNous Research74.52024-07
Meta Llama 3 8B InstructMeta74.52024-07
Meta Llama 3 8B InstructNous Research74.52024-07
Mistral 7B Instruct v0.2Mistral AI73.92024-07
Qwen2 1.5B InstructAlibaba / Qwen Team70.92024-07
falcon 40BTII69.72024-07
deepseek llm 7B baseDeepSeek67.92024-07
deepseek llm 7B chatDeepSeek67.92024-07
phi 2Microsoft64.82024-07
chatglm2 6BZhipu AI60.02024-07
Qwen2 0.5B InstructAlibaba / Qwen Team57.62024-07
gemma 2B itGoogle DeepMind46.12024-07
gemma 2BGoogle DeepMind41.82024-07
deepseek coder 6.7B instructDeepSeek37.62024-07
deepseek coder 6.7B baseDeepSeek37.02024-07
deepseek coder 1.3B baseDeepSeek29.12024-07
deepseek coder 1.3B instructDeepSeek29.12024-07
OLMo 1B hfAllen AI24.82024-07

Data

This page as JSON · Edit on GitHub