ReViCo Benchmark

What is ReViCo?

Evaluates vision-language models on visual text error correction in real-world images, requiring models to identify and fix text errors grounded in visual…

Released

2026-08-27

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 https://arxiv.org/abs/2608.27154

ReViCo paper

• Paper https://arxiv.org/abs/2608.27154

Which sources cite ReViCo?

• ReViCo

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