Artificial Analysis launched Code2Video-AA, its implementation of HeyGen's Code2Video Bench. Models receive 114 design briefs and must produce short product videos as HyperFrames HTML, which is then rendered and judged on five axes. Render success sits at 96% or higher, so the ranking reflects quality rather than whether output runs at all. Claude Opus 5.5 leads the board. Two numbers define the results. Cost per task ranges from $0.01 to $3.89, more than a 300x spread between models, and open-weight models trail the leader by at least 483 Elo points. The benchmark gives teams building code-driven media a direct comparison on the task itself instead of an inference from coding scores.
articleVials Aa
articleThinking Machines Releases Inkling 2 Small Highest Scoring Open Weights Model Outside Of Chinia Upon Weights Release It
articleNanbeige Has Released Nanbeige4 3 33b Scoring 20 On The Intelligence Index
articleGithub Copilot Fusion Orchestrates Anthropic And Openai Models To Balance Performance And Cost
