arena· @arena · X·· 1 天前AI 评分
Claude Haiku 5.5 上线 Arena 的 Agent Arena 与 Code Arena
Anthropic 的 Claude Haiku 5.5 已上线 Arena，用户可前往 Agent Arena 体验，榜单分数即将公布。Agent Arena 基于全球用户提交的数百万真实长程 Agent 任务评测模型，模型可使用 web search、filesystem 和 terminal 工具完成复杂工作流，榜单用因果追踪方法衡量模型相对平均模型的结果表现。
Claude Haiku 5.5 by @AnthropicAI is now in the Arena. Head to Agent Arena to test it out, scores coming soon!
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.
Claude Haiku 5.5 is also available in Code Arena: WebDev, Text, Document and Vision.
来源：arena · x.com