Benchmark Radar™
Star —

Edit2TikZ Benchmark

Explore score history ↗

Edit2TikZ evaluates instruction-guided scientific figure editing with TikZ code, featuring 1,548 samples with textual or visual localization requests and multi-step edits, using a human-aligned evaluation framework to measure edit completion and content preservation.

Released
2026-08-13
Evaluates
Software & AI Compute, Vision & 3D, cs.CV
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

Edit2TikZ paper and code

No reported scores are on record for this benchmark yet.

Which sources cite Edit2TikZ?

Related Software & AI Compute, Vision & 3D, cs.CV benchmarks