Millions of votes a week. One tagging system.
Arena.ai uses a unified tagging system to process millions of votes per week, with a data pipeline built on Databricks and Spark.
入选理由:Arena.ai 每周处理数百万次用户投票,依赖统一标签系统进行分类。
产品
别名:arena.ai
AI模型竞技评测平台。
已收录 4 条与 Arena 相关的内容,按评分排序。
Arena.ai uses a unified tagging system to process millions of votes per week, with a data pipeline built on Databricks and Spark.
入选理由:Arena.ai 每周处理数百万次用户投票,依赖统一标签系统进行分类。
Qwen 3.7 Max Preview ranks 13th in Arena's text domain and 16th in vision domain, both topping Chinese models. Alibaba's LLM iteration pace has significantly accelerated since 2025, with release cycles shortened from 4-6 months to 2-3 months, and nearly monthly updates in 2026, demonstrating sustained acceleration.
入选理由:Qwen 3.7-Max-Preview在Arena文本榜排名第13,是全球前十五唯一中国模型
Qwen3.7 preview version is now on Arena, Alibaba's vision ranking rises to fifth, and the model series will be released soon.
入选理由:Qwen3.7-Plus-Preview在Arena视觉竞技场排名第五,整体排名第十六
The Gemma-4 series of open models ranks #13 (31b) and #17 (26b-a4b) in code performance, marking strong efficiency and local deployability on devices like MBP.
入选理由:Gemma-4-31b在开源代码模型中排名全球第13。