PulseAugur
EN
LIVE 12:42:44
中文(ZH) 编程权威榜单：千问3.7仅次于Claude，阿里全球第二

Alibaba's Qwen3.7-Max ranks second globally on AI programming leaderboard

By PulseAugur Editorial · [4 sources] ·

Alibaba's Qwen3.7-Max has achieved a significant milestone in AI programming capabilities, securing the second global rank on the Code Arena leaderboard with a score of 1541. This places it just behind Anthropic's Claude series and ahead of prominent models like GPT-5.5 and Gemini-3.5-Flash. The Code Arena evaluates models on their ability to generate complete, interactive web applications, distinguishing it from traditional coding benchmarks. Qwen3.7-Max's performance highlights its advanced coding, agent, and long-context task abilities, with developers noting its impressive autonomous execution and cost-effectiveness compared to competitors. AI

IMPACT Sets a new benchmark for AI programming capabilities, challenging existing leaders and highlighting advancements in autonomous task completion.

RANK_REASON The cluster reports on a new benchmark result for an AI model on a respected programming leaderboard.

Read on 量子位 (QbitAI) →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

Alibaba's Qwen3.7-Max ranks second globally on AI programming leaderboard

COVERAGE [4]

  1. 量子位 (QbitAI) TIER_1 中文(ZH) · 量子位的朋友们 ·

    Programming Authority Ranking: Qwen3.7 Second Only to Claude, Alibaba Second Globally

    跻身全球编程模型第一梯队

  2. 36氪 (36Kr) TIER_1 中文(ZH) ·

    Code Arena: Alibaba's Qwen3.7 surpasses GPT and Gemini in programming capabilities, second only to Claude series

    36氪获悉，5月26日凌晨，全球三方编程榜单Code Arena放榜，阿里最新旗舰模型Qwen3.7-Max得分1541，超越GPT-5.5、Gemini-3.5-Flash等一众模型，仅次于Claude系列，在大模型厂商中排名全球第二。

  3. 雷峰网 (Leiphone) TIER_1 中文(ZH) ·

    Code Arena Rankings Released: Alibaba's Qwen3.7 Surpasses GPT and Gemini in Programming Ability, Second Only to Claude Series

    <p>5月26日凌晨，全球权威三方编程榜单Code Arena放榜，阿里最新旗舰模型Qwen3.7-Max得分1541，超越GPT-5.5、Gemini-3.5-Flash、GLM-5.1、Kimi-K2.6等一众模型，仅次于Claude系列，在大模型厂商中排名全球第二，这也标志着在代码理解与生成领域，千问3.7成功跻身全球编程模型第一梯队。</p><p style="text-align: center;">&nbsp;<img src="https://static.leiphone.com/uploads/new/images/20260526/6…

  4. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Alibaba's new Qwen3.7-Max AI model has claimed fourth place on Code Arena's global programming leaderboard with a score of 1,541, beating both OpenAI and Google

    Alibaba's new Qwen3.7-Max AI model has claimed fourth place on Code Arena's global programming leaderboard with a score of 1,541, beating both OpenAI and Google's latest models. The Chinese tech giant is now the only developer besides Anthropic to rank in the top five. https://ww…

    LINKS scmp.com/…/alibabas-new-ai-model-scores-h…

RELATED ENTITIES

RELATED TOPICS