MMLU: High School Macroeconomics

MMLU subject subset: Macroeconomic concepts -- GDP, inflation, fiscal and monetary policy -- at high-school/introductory level.

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
Subcategoryeconomics
Page statusactive
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size390
Dataset licenceMIT
PublisherUC Berkeley (original); Center for AI Safety (current host)

What it measures

Macroeconomic concepts -- GDP, inflation, fiscal and monetary policy -- at high-school/introductory level. Questions are four-option multiple-choice, drawn from the MMLU test set's "economics" subcategory within the benchmark's "social sciences" 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
Meta Llama 3 70BMeta83.82024-07
Meta Llama 3 70B InstructMeta83.82026-04
Meta Llama 3 70B InstructNous Research83.82026-04
Yi 1.5 34B Chat01.AI83.82026-04
Yi 1.5 34B Chat 16K01.AI83.82024-07
Yi 1.5 34B 32K01.AI83.62024-07
Yi 1.5 34B01.AI83.12026-04
Nous Hermes 2 Yi 34BNous Research82.82024-07
Mixtral 8x22B Instruct v0.1Mistral AI81.32026-04
Yi 34B Chat01.AI78.52024-07
Yi 34B 200K01.AI78.22024-07
Yi 1.5 9B Chat01.AI77.92024-07
Yi 1.5 9B Chat 16K01.AI76.22024-07
Yi 9B01.AI75.92024-07
Phi 3 mini 4K instructMicrosoft75.42024-07
Yi 1.5 9B01.AI75.42024-07
Yi 1.5 9B 32K01.AI73.62024-07
Phi 3 mini 128K instructMicrosoft73.32024-07
Yi 1.5 6B01.AI71.02024-07
Mixtral 8x7B v0.1Mistral AI70.52026-04
Mixtral 8x7B Instruct v0.1Mistral AI69.72026-04
Nous Hermes 2 Mixtral 8x7B DPONous Research69.02024-07
Nous Hermes 2 SOLAR 10.7BNous Research67.42024-07
Yi 1.5 6B Chat01.AI66.92024-07
Meta Llama 3 8B InstructMeta65.92024-07
Meta Llama 3 8B InstructNous Research65.92024-07
Hermes 2 Theta Llama 3 8BNous Research65.12024-07
Meta Llama 3 8BMeta65.12024-07
Meta Llama 3 8BNous Research65.12024-07
Yi 6B01.AI64.92024-07
Yi 6B Chat01.AI64.92024-07
gemma 7B itGoogle DeepMind64.62024-07
Hermes 2 Pro Llama 3 8BNous Research62.12024-07
Mistral 7B v0.3Mistral AI60.52024-07
mistral 7B v0.3 bnb 4bitUnsloth60.52024-07
Qwen2 1.5B InstructAlibaba / Qwen Team58.52024-07
phi 2Microsoft58.22024-07
Mistral 7B Instruct v0.2Mistral AI55.62024-07
falcon 40BTII55.42024-07
deepseek llm 7B baseDeepSeek46.72024-07
deepseek llm 7B chatDeepSeek46.72024-07
Qwen2 0.5B InstructAlibaba / Qwen Team45.92024-07
chatglm2 6BZhipu AI44.92024-07
gemma 2BGoogle DeepMind41.02024-07
deepseek coder 6.7B instructDeepSeek35.62024-07
deepseek coder 6.7B baseDeepSeek34.62024-07
gemma 2B itGoogle DeepMind32.82024-07
OLMo 1B hfAllen AI27.22024-07
deepseek coder 1.3B baseDeepSeek26.92024-07
deepseek coder 1.3B instructDeepSeek26.92024-07

Data

This page as JSON · Edit on GitHub