Benchmark Radar™
Star —

VeriOCRBench

Explore score history ↗

Evaluates OCR-grounded task verification with 1,800 human-verified samples including 1,600 trap-injected invalid tasks and 200 controls, scored via TVR, DA, and ORR.

Released
2026-08-31
Evaluates
General AI, Reasoning, Vision & 3D
Openness
unknown
Importer
Claire Radar
Review status
ai-reviewed

VeriOCRBench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite VeriOCRBench?

Related General AI, Reasoning, Vision & 3D benchmarks