VIABLE Benchmark

What is VIABLE?

A benchmark of over 300K judgment samples that evaluates VLM judges for visually impaired assistance on effectiveness, impartiality, and stability.

Released

2026-05-29

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.31351

VIABLE paper and code

• Paper https://arxiv.org/abs/2605.31351
• Code https://github.com/YiyiyiZhao/VIABLE

Which sources cite VIABLE?

• VIABLE

Related General AI, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench