MMLU: US Foreign Policy

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

Also known as: us_foreign_policy

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
SubcategorySocial Sciences
Page statusactive
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size100
Dataset licenceMIT
PublisherUC Berkeley

What it measures

The history and theory of US foreign policy: diplomacy, treaties, foreign-policy doctrines, and the institutions (the State Department, the National Security Council) that carry it out. 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
Mixtral 8x22B Instruct v0.1Mistral AI96.02026-04
Yi 1.5 9B 32K01.AI93.02024-07
Yi 1.5 9B Chat 16K01.AI93.02024-07
Meta Llama 3 70BMeta92.02024-07
Meta Llama 3 70B InstructMeta92.02026-04
Meta Llama 3 70B InstructNous Research92.02026-04
Mixtral 8x7B v0.1Mistral AI92.02026-04
Nous Hermes 2 Yi 34BNous Research92.02024-07
Yi 1.5 34B 32K01.AI92.02024-07
Yi 34B 200K01.AI92.02024-07
Nous Hermes 2 Mixtral 8x7B DPONous Research91.02024-07
Nous Hermes 2 SOLAR 10.7BNous Research91.02024-07
Yi 1.5 9B01.AI91.02024-07
Yi 1.5 9B Chat01.AI91.02024-07
Mixtral 8x7B Instruct v0.1Mistral AI90.02026-04
Yi 1.5 34B01.AI90.02026-04
Yi 9B01.AI90.02024-07
Yi 34B Chat01.AI89.02024-07
gemma 7B itGoogle DeepMind88.02024-07
Mistral 7B v0.3Mistral AI88.02024-07
mistral 7B v0.3 bnb 4bitUnsloth88.02024-07
Phi 3 mini 128K instructMicrosoft87.02024-07
Hermes 2 Theta Llama 3 8BNous Research86.02024-07
Meta Llama 3 8BMeta86.02024-07
Meta Llama 3 8BNous Research86.02024-07
Meta Llama 3 8B InstructMeta86.02024-07
Meta Llama 3 8B InstructNous Research86.02024-07
Yi 1.5 34B Chat01.AI86.02026-04
Yi 1.5 34B Chat 16K01.AI86.02024-07
Yi 1.5 6B01.AI86.02024-07
Phi 3 mini 4K instructMicrosoft85.02024-07
Yi 6B01.AI85.02024-07
Yi 6B Chat01.AI85.02024-07
Hermes 2 Pro Llama 3 8BNous Research84.02024-07
deepseek llm 7B baseDeepSeek82.02024-07
deepseek llm 7B chatDeepSeek82.02024-07
falcon 40BTII81.02024-07
Mistral 7B Instruct v0.2Mistral AI81.02024-07
Yi 1.5 6B Chat01.AI81.02024-07
Qwen2 1.5B InstructAlibaba / Qwen Team79.02024-07
phi 2Microsoft77.02024-07
chatglm2 6BZhipu AI73.02024-07
Qwen2 0.5B InstructAlibaba / Qwen Team65.02024-07
gemma 2B itGoogle DeepMind64.02024-07
gemma 2BGoogle DeepMind57.02024-07
deepseek coder 6.7B instructDeepSeek54.02024-07
deepseek coder 6.7B baseDeepSeek49.02024-07
deepseek coder 1.3B baseDeepSeek32.02024-07
deepseek coder 1.3B instructDeepSeek32.02024-07
OLMo 1B hfAllen AI30.02024-07

Data

This page as JSON · Edit on GitHub