Artificial Analysis launches Code2Video-AA, ranking 27 models on making marketing videos in code; Claude Opus 5.5 leads
Artificial Analysis presents Code2Video-AA, its independent implementation of HeyGen's Code2Video Bench. Models receive one design brief from 114 and write a HyperFrames HTML composition using HTML and GSAP, which is rendered to video. A Gemini 4 Argon judge compares pairs of videos without seeing model names across five axes: engagement, prompt intent, composition, temporal consistency and craft. Each axis gets its own Elo rating, and the overall Elo is their mean. The page reports 27 models, with Claude Opus 5.5 at 1536 and Claude Sonnet 5.5 at 1443 as top scores, along with cost, token usage and time per task.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · source check open
- Discovery linkX
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Artificial Analysis presents Code2Video-AA, its independent implementation of HeyGen's Code2Video Bench. Models receive one design brief from 114 and write a HyperFrames HTML composition using HTML and GSAP, which is rendered to video. A Gemini 4 Argon judge compares pairs of videos without seeing model names across five axes: engagement, prompt intent, composition, temporal consistency and craft. Each axis gets its own Elo rating, and the overall Elo is their mean. The page reports 27 models, with Claude Opus 5.5 at 1536 and Claude Sonnet 5.5 at 1443 as top scores, along with cost, token usage and time per task.
Key findings from the stored brief
- Models write one HyperFrames HTML composition per brief, which is rendered to video for judging.
- A Gemini 4 Argon judge compares two models' videos per brief without seeing model names, one call per axis.
- Overall Elo is the mean of five per-axis Elo ratings, anchored to GPT-5.5 (xhigh) at 1000.
- Claude Opus 5.5 scores highest at 1536, followed by Claude Sonnet 5.5 at 1443 and GPT-6 Astra at 1427.
Rankings rely on an LLM judge (Gemini 4 Argon) comparing videos; the source claims not independently checked by this abstract.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
It offers a reproducible, judge-based way to compare models on generating short marketing videos through code, covering cost, tokens and speed alongside quality.
Limits and open questions
Rankings rely on an LLM judge (Gemini 4 Argon) comparing videos; the source claims not independently checked by this abstract.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Ask about the source, add context, or point readers to a relevant follow-up.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.