Frontend Code Arena: Opus 5 Max Takes #1, Kimi K3 Max Follows Closely
arena · x · 2026-07-28
Arena has released its latest WebDev AI Leaderboard, based on nearly 500,000 votes.
- Top Rankings: Anthropic's claude-opus-5-max takes the #1 spot with a score of 1725. Moonshot's kimi-k3-max follows closely at #2 overall and #1 among open-weight models with 1682 points.
- Other Models: claude-fable-5 (#4) and gpt-5.6-sol-xhigh (#5) show very competitive performance. Among open-weight models, Zhipu's glm-5.2-max ranks 6th.
- Pricing: The leaderboard also reveals API pricing, such as Kimi K3 Max at $3/$15 (input/output per million tokens), while Opus 5 Max pricing is currently listed as N/A.
More from Models
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- Fully local voice assistant on an RTX 3060 replicates the GPT Live demo in 6.5 minutes — liampetti · 2026-09-11
- Meta's Muse Agent has built-in invite code logic, hinting at free-usage expansion — testingcatalog · 2026-09-11