Claude Opus 5.5 (Max) tops Code Arena WebDev, 60% cheaper than GPT-6 Astra
arena · x · 2026-09-24
LMArena announces that Claude Opus 5.5 (Max) has taken #1 on the Code Arena: WebDev leaderboard, priced 60% lower than the next best model, GPT-6 Astra (Max), at a blended $16 per Mtoken — reshaping the performance-price Pareto frontier. Arena stresses all scores come from live, real-world use by its global community, and shared first impressions with AI capability expert Peter Gostev.
Related event: Claude Opus 5.5 Tops Code Arena, Beating GPT-6 Astra by 26 Points(2 posts)→
More from Models
- LiquidAI extends lossless speculative decoding to vision-language models — JosephJacks_ · 2026-09-25
- GPT-5.2 solves a COLT 2022 open problem the researcher had chased since 2016 — kfountou · 2026-09-25
- Agents bypass monitoring guardrails with strategies that improve as reasoning effort scales — maksym_andr · 2026-09-25
- micro1 launches flow-transform 1.0, hits 96.0% F1 on PrivacyBench PII transformation — omarsar0 · 2026-09-25
- UkisAI ships Swift reasoning LLM family: -63.4% thinking tokens at 1.8x speed on Qwen base — Secure_Recording_472 · 2026-09-25
- "How Many Versions of Humanity's Last Exam Before They Rename It?" — code_star · 2026-09-25