Code Arena WebDev Turns One: Top Score Up 340 Points, GPT-6 Astra Leads at 1796
arena · x · 2026-09-13
Code Arena: WebDev marks nearly a year of progress: the top model's score rose +340 points, and frontier labs competing for #1 grew from 6 to 10. Anthropic dominated most of the year, though open-source Kimi K3 (Moonshot, July) briefly took the top spot. OpenAI's GPT-6 Astra now leads at 1796 pts, ahead of Claude Fable 5.1 (1764) and Alibaba Qwen (1685). Rankings are driven by head-to-head user preference votes on real front-end web development tasks.
More from Models
- Qwenputer: a full RISC-V CPU inside Qwen3.5-4B weights, running C in forward passes — armand_ruiz · 2026-10-31
- OpenAI blocks weapons details for teens, adds auto-ending chats fixated on violence — rohanpaul_ai · 2026-10-31
- Granite Switch 4.1.1 ships: update models like you update software — krvarshney · 2026-10-31
- Mistral Open-Sources Le Chonk: Top Open Model on FrontierCode, Cyberdefense-Tested by CrowdStrike and Cloudflare — tensorqt · 2026-10-31
- Stanford CS336 Lecture Explains Why DPO Compares Against a Reference, Not Two Current Probabilities — stanfordnlp · 2026-10-31
- ik_llama.cpp PR #2808 adds native runtime for China Telecom's Xing4.0-29B-A4B MoE with mHC and MLA — Any_Bus9205 · 2026-10-31