LL-Bench

What is LL-Bench?

LL-Bench evaluates large-scale generative models on 16 low-level vision tasks using 2,469 real-world degraded images, with human preference and quality score…

Released

2026-06-01

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.02535

LL-Bench paper

• Paper https://arxiv.org/abs/2606.02535

Which sources cite LL-Bench?

• LL-Bench

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