Code2Video-AA benchmark places Claude Opus 5.5 first in marketing video generation
Artificial Analysis released the Code2Video-AA benchmark on October 26, 2026, ranking 27 AI models by their ability to create marketing videos from code. The test requires models to generate HyperFrames HTML compositions and GSAP animations based on 114 product and brand marketing briefs. Scores come from blind pairwise comparisons across five axes: engagement, prompt intent, composition,…
Key points
- Claude Opus 5.5 scored highest with an Elo rating of 1536, outperforming 26 other models in Code2Video-AA benchmark
- Task costs varied from $0.01 to $3.89, with GPT-6.1 Sol priced at approximately $0.31 per output
- Open-weight models scored around 1052–1053, trailing top models by roughly 480 Elo points
Model pages: Claude Opus 5.5 → · Claude Sonnet 5.5 → · GPT-6 Astra →
The story so far
2 episodes →- Code2Video-AA benchmark places Claude Opus 5.5 first in marketing video generationthis story
Code2Video-AA benchmark ranks Claude Opus 5.5 first among 27 AI models at making marketing videos from code
cryptobriefing.com · 26 October 2026
Loading the full article…
This text was published by cryptobriefing.com and written by Diego Almada Lopez. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Marketing & Small Business
All →- Google lets Gemini edit Google Keep lists and notes via Workspace integration · 1 src
- Apple adds Siri AI to French, Japanese, Korean, Portuguese and Spanish in iOS 27.2 · 3 src
- Shopify adds built‑in Knowledge base to admin · 1 src
- Google unveils Gemini 3.5, Omni video AI and Spark agent at I/O · 2 src
- ChatGPT directs tech issues to 404 Media · 2 src
Comments
via GitHub Discussions