Benchmark RadarAI BENCHMARK PROFILE
MORE
MORE evaluates multilingual document parsing across 149 languages, covering text, formulas, tables, code blocks, catalogs, and reading order, using 1,288 real-world document images with human-refined annotations.
- Released
- 2026-07-03
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Existing benchmarks focus on high-resource languages, leaving a gap in assessing multilingual document parsers. MORE provides a broad and structured evaluation to compare model capabilities on low-resource languages and diverse document elements.
Motivation
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.