SynthDocBench

What is SynthDocBench?

SynthDocBench evaluates vision-language models on 1,788 questions over 200 synthetic long-context documents (avg. 51.1 pages) with 3,340 charts. It varies…

Released

2026-07-11

Evaluates

General AI, Long Context, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.10400

SynthDocBench paper and code

• Paper https://arxiv.org/abs/2607.10400
• Code https://github.com/ServiceNow/SynthDocBench

Which sources cite SynthDocBench?

• SynthDocBench

Related General AI, Long Context, Vision & 3D benchmarks

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