List your company

React UI Generation on Cookie-Bench Overall

84.2Total ScoreOpus 4.7
60.38466.56772.7578.933May 28, 2026

Evaluation results

MethodLinks
Opus 4.7Generation Mode=HTML direct chat2026.0584.2
Opus 4.7Generation Mode=React agent scaffold2026.0583.3
Opus 4.6Generation Mode=React agent scaffold2026.0580
Kimi-K2.6Generation Mode=HTML direct chat2026.0578.9
Opus 4.6Generation Mode=HTML direct chat2026.0578.9
GPT-5.4Generation Mode=HTML direct chat2026.0578.6
Kimi-K2.6Generation Mode=React agent scaffold2026.0578.3
GPT-5.4Generation Mode=React agent scaffold2026.0577.8
Mimo-V2-ProGeneration Mode=React agent scaffold2026.0576.3
GLM-5.1Generation Mode=React agent scaffold2026.0576.2
GLM-5.1Generation Mode=HTML direct chat2026.0576.1
Qwen3.6-PlusGeneration Mode=React agent scaffold2026.0575.2
DS-V4-ProGeneration Mode=HTML direct chat2026.0574.6
Qwen3.6-PlusGeneration Mode=HTML direct chat2026.0574.4
Mimo-V2-ProGeneration Mode=HTML direct chat2026.0573.9
Gemini-3.1-ProGeneration Mode=HTML direct chat2026.0573.5
DS-V4-ProGeneration Mode=React agent scaffold2026.0573.2
DS-V4-FlashGeneration Mode=HTML direct chat2026.0572.6
Qwen3.6-27BGeneration Mode=HTML direct chat2026.0570.7
DS-V4-FlashGeneration Mode=React agent scaffold2026.0567.9
Qwen3.6-27BGeneration Mode=React agent scaffold2026.0567.2
Gemini-3-FlashGeneration Mode=HTML direct chat2026.0566.1
Gemini-3.1-ProGeneration Mode=React agent scaffold2026.0564.9
Gemini-3-FlashGeneration Mode=React agent scaffold2026.0563.3
Qwen3.6-35B-A3BGeneration Mode=HTML direct chat2026.0563.1
Qwen3.6-35B-A3BGeneration Mode=React agent scaffold2026.0561.3