Arena.ai (@arena) · 10/11/2026, 01:15:28
Claude Opus 5.5 Tops Image-to-WebDev Arena with 1749 Points, Sonnet 5.5 Close Behind at Half Cost
Anthropic's Claude Opus 5.5 (Max) secured the #1 spot in the Image-to-WebDev Arena benchmark with 1749 points, outperforming GPT-6 Astra. Its sibling model, Claude Sonnet 5.5 (xHigh), ranked second with only a 9-point gap but offered significantly better cost-efficiency at $8/M compared to Opus's $16/M. Both models landed on the Pareto frontier, demonstrating optimal trade-offs between performance and cost for image-to-code generation and agentic workflows.
SOURCE COVERAGEFull Original Report
Arena.ai (@arena) · 2026-10-10 17
Image-to-WebDev Arena update: Claude Opus 5.5 (Max) by @AnthropicAI takes the #1 spot with 1749 pts, with Claude Sonnet 5.5 (xHigh) just 9 pts behind at #2 with 1740 pts!
Both models also landed on the Pareto frontier! See their positioning on the visual in thread.
- #1-ranked Claude Opus 5.5 (Max) has a blended input/output token price of 40/M.
- #2-ranked Claude Sonnet 5.5 (xHigh) costs $8/M, 50% less than Opus for a 9-point score gap. It also ranks one place above GPT-6 Astra (#3) while costing 80% less.
Stay tuned to see where Claude Haiku 5.5 lands in the Image-to-WebDev Arena!
The Image-to-WebDev Arena ranks AI models on their ability to generate websites from images and screenshots, alongside agentic coding workflows involving multi-step reasoning and tool use.
