Alibaba's Qwen3.8-Max-0902 model has achieved the top position in the Code Arena: WebDev competition, scoring 1691 points. This new model surpasses previous benchmarks, outperforming Claude Opus 5 by 3 points, Kimi K3 by 17 points, and its predecessor Qwen3.8-Max by 22 points. The model is priced at $5/MToken. AI
IMPACT Sets a new standard in coding benchmarks, potentially influencing future model development and competition.
RANK_REASON New benchmark result for a model from a major lab. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →