WildHandBench

What is WildHandBench?

A benchmark containing 500 handwritten documents across three structures, four languages, and nine real-world scenarios, with a Prior-Driven Error metric to…

Released

2026-08-24

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence http://arxiv.org/abs/2608.22959v1

WildHandBench paper

• Paper http://arxiv.org/abs/2608.22959v1

Which sources cite WildHandBench?

• WildHandBench

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench