Benchmark Radar
AI BENCHMARK PROFILE

ALD/E-ImageMiner

General AIMultimodal Perception

ALD/E-ImageMiner is a benchmark of 1,951 scientific figures from 205 publications, expert-annotated for classification, table extraction, summarization, and visual question answering.

Released
2026-08-14
Readiness
Paper only
Primary field
General AI

Why it matters

It enables evaluation on scientific figure understanding, connecting a competition to broader aims in scientific visual knowledge and multimodal AI.

Motivation

Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret.

Primary resources

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