Atlas

Benchmarks

Co-Design Bench Multimodal Editing

arXiv

Strict completion on Co-Design Bench's 100 Multimodal Editing tasks: localized visual, structural and content edits to a runnable page, given an annotated target region and, for 80 tasks, an image, video, audio or document attachment. Its 553 hidden criteria, about 5.5 per task, also check that unrelated content is preserved when the request asks for it.

Models
10
Top score
75.4
Leader
GPT-6 Astra
Updated
Oct 26, 2026
Resolution
—
Saturation
—
Signal
30thpercentile
205 benchmarks from 0.8 to 3.6219 benchmarks from 3.6 to 6.4134 benchmarks from 6.4 to 9.393 benchmarks from 9.3 to 12.155 benchmarks from 12.1 to 14.925 benchmarks from 14.9 to 17.713 benchmarks from 17.7 to 20.55 benchmarks from 20.5 to 23.37 benchmarks from 23.3 to 26.27 benchmarks from 26.2 to 29.01 benchmark from 29.0 to 31.83 benchmarks from 31.8 to 34.66 benchmarks from 34.6 to 37.43 benchmarks from 37.4 to 40.21 benchmark from 40.2 to 43.11 benchmark from 45.9 to 48.71 benchmark from 65.6 to 68.4

547th strongest of 779

Signal-to-noise +3.91 for the Co-Design Bench family

Difficulty
Not estimated

Another benchmark represents this family in the fit.

10 dated models · 4 frontier modelsClosed weightsOpen weights
Data: Co-Design Bench Authorsatlas.village.dev
Loading Atlas data…