WebDev AI Arena: Claude Dominates Leaderboard, Kimi Takes Second
arena · x · 2026-08-01
LMSYS has updated its WebDev AI Leaderboard, ranking frontier models on front-end web development tasks based on over 500,000 community votes. The evaluation includes agentic coding workflows requiring multi-step reasoning and tool use.
Top Contenders:
- claude-opus-5-max (Anthropic) ranks 1st with a score of 1704, priced at $5/$25 per million tokens.
- kimi-k3-max (Moonshot) takes an impressive 2nd place at 1675 points, offering significant cost efficiency at $3/$15.
- claude-opus-5-high (1664) and claude-fable-5 (1630) follow, giving Anthropic a clean sweep of the top four.
Other Major Models:
- OpenAI's gpt-5.6-sol-xhigh sits at 5th (1621).
- Among open-source models, Z.ai's glm-5.2-max (1587) and DeepSeek's deepseek-v4-flash-high (1586) break into the top tier, with the latter featuring an ultra-low price of $0.14/$0.28.
Related event: Claude Opus 5 Tops AI Leaderboards for Web Development and Image-to-Code(4 posts)→
More from Models
- Four Gemini 4 Argon agents beat Minecraft's Ender Dragon in 27 hours with 2,783 self-written programs — robertarail · 2026-10-16
- Mistral touts STEM benchmark win, but leaderboard shows it ranking sixth overall — MistralAI · 2026-10-16
- Local tool calling compared: how Gemma 4, Llama 3 and Mistral differ — leslysandra · 2026-10-16
- $2 Gemini Pro accounts flood the gray market, spawning waves of AI spam comments — huangyun_122 · 2026-10-16
- Haider: Opus 5.5 vs Astra on SWE tasks — Astra has a higher floor, reasoning in a tier of its own — haider1 · 2026-10-16
- Artificial Analysis launches Decision Index for the emerging decision model category — ArtificialAnlys · 2026-10-16