SciFigQual-Bench

What is SciFigQual-Bench?

A benchmark for evaluating scientific figure quality across five dimensions with full-manuscript context, using 6,308 expert-rated images from top CS…

Released

2026-07-29

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/2607.27084

SciFigQual-Bench paper and code

• Paper https://arxiv.org/abs/2607.27084
• Code https://github.com/FrankDengAI/SciFigQual-Bench
• Website https://frankdengai.github.io/SciFigQual-Bench

Which sources cite SciFigQual-Bench?

• SciFigQual-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