Image-to-WebDev Arena Pareto Frontier: Open Models Hit 92% of Claude at $0.17/M
arena · x · 2026-10-11
Arena published the full Pareto frontier for its Image-to-WebDev Arena (177K votes, 64 models). Beyond Anthropic's 1-2 finish, open-source models stand out on price-performance:
- claude-opus-5.5-max: 1749 pts, $16/M
- claude-sonnet-5.5-xhigh: 1740 pts, $8/M
- Meta muse-spark-1.3-max: 1642 pts, $3.50/M
- DeepSeek deepseek-v4.1-flash (MIT): 1609 pts, $0.97/M
- Xiaomi mimo-v2.6-flash (MIT): 1597 pts, $0.25/M
- GLM glm-5.3-flash (MIT): 1581 pts, $0.17/M
For screenshot-to-code and agentic coding, top open models now reach 92% of closed flagship scores at under $1/M.
Related event: Claude Opus 5.5 Tops Image-to-WebDev Arena(2 posts)→
More from Models
- Anonymous unreleased AI model builds impressive pure-code three.js in hours — karminski3 · 2026-10-11
- Researcher Breaks Qwen 2.5 via Endless Gaslighting, Forced Off arXiv by Endorsement Rule — IndraVahan · 2026-10-11
- Outside CVP/Daybreak, the world's best cybersecurity model is Chinese GLM 5.3, not Claude — zephyr_z9 · 2026-10-11
- Was Claude's gibberish fixed by capping KL divergence in RL? One theory — burny_tech · 2026-10-11
- 20-year engineer benchmarks Gemma4-31B vs Qwen3.8-27B locally; GPT-6.1-Sol is still another tier — therealjerseytom · 2026-10-11
- Rumor: Google employees claim internal model Carbon beats unreleased Gemini — bindureddy · 2026-10-11