想对比主流模型在真实任务中的智能体能力？Agent Arena 用 30 万+任务和 200 万+工具调用给出了量化排名，做 AI 应用选型的团队可以直接参考排行榜做决策。
Anthropic 的 Claude Fable 5 模型已上线 Agent 模式，用户可在 Agent Arena 中测试其智能体能力。Agent Arena 是一个基于真实用户任务的智能体评估平台，通过数百万次实时会话衡量模型在代码编写、网页搜索、文件操作等复杂工作流中的表现。排行榜基于 30 万+任务、200 万+工具调用和 4000 万行代码构建，当前排名第一的是 OpenAI 的 GPT-5.5 (High)，Claude-Opus-4.7 (Thinking) 位列第二。评估信号包括任务成功率、可操控性、错误恢复、用户反馈和工具幻觉等。
Claude Fable 5 by @AnthropicAI is in Agent Mode! Come test out its agentic capabilities for accomp...
Claude Fable 5 by @AnthropicAI is in Agent Mode! Come test out its agentic capabilities for accomplishing your real-world tasks. Every session contributes to the Agent Arena leaderboard. We'll see scores soon. Arena.ai @arena Introducing Agent Arena: real-world agentic evals at scale. How do you evaluate agents doing actual work? We measure millions of live sessions where real users accomplish real tasks. On Arena, models now get web search, filesystem, and terminal tools to complete complex workflows: writing code, creating slide deck, researching the web, building apps, and analyzing documents. Every session produces rich signals. Users iterate with the agent turn-by-turn: approving, editing, correcting, praise or expressing frustration. The environment gives feedback too: shell errors, tool failures, recovery attempts, and more. Our leaderboard measures each model's agentic performance using causal inference across five signals: task success, steerability, error recovery, user praise vs. complaint, and tool hallucination. This leaderboard snapshot is built from 300K+ tasks, 2M+ tool calls, and 40M lines of code by agents. Top labs in Agent Arena: - #1 @OpenAI : GPT-5.5 (High) - #2 @AnthropicAI : Claude-Opus-4.7 (Thinking) - #3 @Zai_org : GLM-5.1 - #4 @GoogleDeepMind : Gemini-3.1-Pro - #5 @Kimi_Moonshot : Kimi-K2.6 More analysis in the thread, with the full technical blog below. 🔗 View Quoted Tweet 💬 6 🔄 3 ❤️ 59 👀 3115 📊 9 ⚡