Benchmark

ARC-E

ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning…

Modality
text
Categories
reasoning, general
Openness
unknown
Source
llm_stats
Reported scores
8

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
ERNIE 4.5Baidu0.6072025-06-25evidence
Gemma 2 27BGoogle0.8862024-06-27evidence
Gemma 2 9BGoogle0.882024-06-27evidence
Gemma 3n E2BGoogle0.7582025-06-26evidence
Gemma 3n E2B Instructed LiteRT (Preview)Google0.7582025-05-20evidence
Gemma 3n E4BGoogle0.8162025-06-26evidence
Gemma 3n E4B Instructed LiteRT PreviewGoogle0.8162025-05-20evidence
Hermes 3 70BNous Research0.82952024-08-15evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.