MMLU: College Chemistry

MMLU subject subset: General and organic chemistry at the undergraduate 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
Subcategorychemistry
Page statusactive
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size100
Dataset licenceMIT
PublisherUC Berkeley (original); Center for AI Safety (current host)

What it measures

General and organic chemistry at the undergraduate level. Questions are four-option multiple-choice, drawn from the MMLU test set's "chemistry" 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 9B Chat01.AI59.02024-07
Yi 1.5 34B01.AI57.02026-04
Meta Llama 3 70BMeta56.02024-07
Meta Llama 3 70B InstructMeta56.02026-04
Meta Llama 3 70B InstructNous Research56.02026-04
Mixtral 8x22B Instruct v0.1Mistral AI56.02026-04
Yi 1.5 34B Chat01.AI56.02026-04
Yi 1.5 34B Chat 16K01.AI56.02024-07
Nous Hermes 2 Mixtral 8x7B DPONous Research55.02024-07
Mixtral 8x7B v0.1Mistral AI54.02026-04
Yi 1.5 9B Chat 16K01.AI54.02024-07
Yi 9B01.AI54.02024-07
Yi 1.5 9B01.AI53.02024-07
Yi 34B Chat01.AI53.02024-07
Yi 1.5 34B 32K01.AI52.02024-07
Nous Hermes 2 Yi 34BNous Research51.02024-07
Mixtral 8x7B Instruct v0.1Mistral AI50.02026-04
Mistral 7B v0.3Mistral AI49.02024-07
mistral 7B v0.3 bnb 4bitUnsloth49.02024-07
Yi 1.5 9B 32K01.AI49.02024-07
Hermes 2 Theta Llama 3 8BNous Research48.02024-07
gemma 7B itGoogle DeepMind47.02024-07
Meta Llama 3 8BMeta47.02024-07
Meta Llama 3 8BNous Research47.02024-07
Meta Llama 3 8B InstructMeta47.02024-07
Meta Llama 3 8B InstructNous Research47.02024-07
Nous Hermes 2 SOLAR 10.7BNous Research47.02024-07
Phi 3 mini 4K instructMicrosoft47.02024-07
Yi 34B 200K01.AI47.02024-07
falcon 40BTII45.02024-07
Yi 1.5 6B Chat01.AI45.02024-07
Phi 3 mini 128K instructMicrosoft44.02024-07
Yi 1.5 6B01.AI44.02024-07
Yi 6B01.AI43.02024-07
Yi 6B Chat01.AI43.02024-07
Hermes 2 Pro Llama 3 8BNous Research41.02024-07
chatglm2 6BZhipu AI40.02024-07
Mistral 7B Instruct v0.2Mistral AI40.02024-07
phi 2Microsoft40.02024-07
deepseek coder 6.7B baseDeepSeek39.02024-07
Qwen2 1.5B InstructAlibaba / Qwen Team38.02024-07
deepseek llm 7B baseDeepSeek37.02024-07
deepseek llm 7B chatDeepSeek37.02024-07
gemma 2BGoogle DeepMind37.02024-07
deepseek coder 6.7B instructDeepSeek36.02024-07
Qwen2 0.5B InstructAlibaba / Qwen Team28.02024-07
gemma 2B itGoogle DeepMind26.02024-07
deepseek coder 1.3B baseDeepSeek25.02024-07
deepseek coder 1.3B instructDeepSeek25.02024-07
OLMo 1B hfAllen AI20.02024-07

Data

This page as JSON · Edit on GitHub