Agent Arena 排行榜上线：用真实长程智能体任务评测模型
LMArena 团队搞了个 Agent Arena 榜，不用考试题，直接看模型配搜索、终端工具干真实活儿的结果，选模型前可以去看看。
Agent Arena 排行榜基于全球用户贡献的数百万条真实智能体任务对模型进行评测，任务为长程复杂工作流。模型在评测中可以使用网页搜索、文件系统和终端工具完成操作。
排名采用因果追踪（causal tracing）方法，衡量各模型结果相对于平均水平模型的表现。榜单详情公布在 arena.
ai 的 leaderboard 页面。
In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks from a global community of users. Models can access web search, filesystem, and terminal tools to complete complex workflows. The leaderboard measures model performance on outcomes relative to the average model using a causal tracing methodology. See the Agent Arena leaderboard details at: arena.ai/leaderboard/ag…
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Agent Arena, LMArena, agents, model evaluation.
Source attribution: curated from lmarena.ai (@lmarena_ai).
