Image-to-WebDev Arena: GPT-6 Astra tops at 1733, GLM-5.3-Flash shines on price
arena · x · 2026-09-16
Four new models landed on LMArena's Image-to-WebDev leaderboard:
- #1 GPT-6 Astra (Max) (OpenAI, 1733 pts): 129 above GPT-5.6 Sol (xHigh), 23 above #2, at $40/M blended
- #2 Claude Fable 5.1 (Max) (Anthropic, 1710): 87 above Fable 5, 45 above Claude Opus 5 (Max, 1665)
- #4 Muse Spark 1.3 (Max) (Meta, 1645) at $3.50/M
- #10 GLM-5.3-Flash (Z.ai, 1588) at just $0.21/M
GPT-6 Astra, Muse Spark 1.3, and GLM-5.3-Flash all sit on the Pareto frontier. The leaderboard tests image/screenshot-to-website generation plus agentic coding workflows, with 128k votes across 50 models.
More from coding & agent
- Tencent unveils Hyra 2.0, a research agent that builds reusable scientific tools — TencentHunyuan · 2026-11-02
- General Reasoning explains how to train agent swarms with RL and latency pressure — rosstaylor90 · 2026-11-02
- "Coding isn't the bottleneck anymore — usage windows are," says founder Kyle Gawley — kylegawley · 2026-11-02
- Demo passed ≠ production-ready: 5 questions to answer before letting agents run your business — _kellhus · 2026-11-02
- An AI agent passed 100 test chats—still not ready to run the business — djgoel123 · 2026-11-02
- Agent given total creative freedom produces a 1:44 code-drawn animated short film — ivegotnoidea1 · 2026-11-02