Benchmark
PubTables-1M
A large-scale table structure recognition dataset for scientific documents containing nearly one million tables, used to train and evaluate table detection and structure recognition models.
Timeline (last 90 days)
Oct 18
Spartan currently lacks formal benchmark evaluation (e.g., using GriTS or TEDS on ICDAR 2013/PubTables-1M/FinTabNet), which is its biggest shortcoming.
Unverified50%