Directory label

Document Understanding: AI benchmarks

A label other catalogs put on entries, not one of the domains on our map. On the map, each entry here sits in the domain its own site or paper leads with.

AI benchmarks
23
Shares entries with
1 category

Snapshot 2026-11-07. How categories are built · Where the data comes from

In short

What are the main document understanding benchmarks?
CiteVQA, DocScope, DocAtlas, MechVQA, MMDocBench and RPC-Bench, among 22 confirmed below.

Only benchmarks use the Document Understanding tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 23

  1. CiteVQAOpenDataLab
  2. DocScopeAlibaba Group, MiliLab, Wuhan University
  3. DocAtlasMBZUAI
  4. MechVQA
  5. MMDocBench
  6. RPC-Bench
  7. VAREX-Bench
  8. MORE
  9. BIM-Edit
  10. ChartFI
  11. SIN-Bench
  12. Doc-PP
  13. Dr. DocBench
  14. pdfQA
  15. VotIE: Information Extraction from Meeting Minutes
  16. ChartREG++
  17. DocILERossum.ai
  18. DUE Benchmark
  19. PubTables-1MMicrosoft
  20. LongDocURL
  21. Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images
  22. PulseBench-Tab
1 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. Self-Ensembling Vision-Language Models for Chart Data Extraction

Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.