STEM

A comprehensive multimodal benchmark dataset with 448 skills and 1,073,146 questions spanning all STEM subjects (Science, Technology, Engineering, Mathematics), designed to test neural models' vision-language STEM skills based on K-12 curriculum. Unlike existing datasets that focus on expert-level ability, this dataset includes fundamental skills designed around educational standards.

Released

Unknown

Readiness

Paper only

Primary field

General AI

Benchmark Radar records only publicly supported details and links back to primary sources for verification.