Arena 推出 Agent Arena Index,Claude Fable 5.2 (Max) 以 1463 分居首
智能体排行榜终于细分了,不再是一个笼统总分。Claude Fable 5.2 (Max) 拿下 1463 分领先 Gemini 和 GPT-6 一大截,选模型接活之前先看看这几个分项榜单再决定。
LMArena(Arena.ai)发布 Agent Arena Index,作为衡量智能体综合表现的新指标,同时推出 Agentic Work、Coding、Chat、Task Outcomes、Tool Use、Steering 六个细分榜单。这些分数基于全球社区数百万条真实任务数据统计得出。
Claude Fable 5.2 (Max) 以 1463 分领跑 Agent Arena Index,领先第二名 134 分。前五名依次为:Anthropic(1463 分)、Google DeepMind 的 Gemini 4 Carbon (High)(1307 分)、OpenAI 的 GPT-6 Astra (Max)(1274 分)、Meta 的 Muse Wonder Full (Max)(1200 分)、阿里巴巴的 Qwen4-Max (xHigh)(1191 分)。
该指数综合四项真实使用信号:任务完成确认、用户表扬与投诉比、终端工具使用可靠性(Bash Reliability)以及对用户纠正的响应能力(Steerability)。配套的 Alignment Index 则从欺骗性完成、未经授权操作、虚假归因三方面衡量智能体是否忠实执行用户意图。
Today, we’re excited to introduce the Agent Arena Index, our new headline measure of overall agent performance, alongside six new focused indexes: Agentic Work, Coding, Chat, Task Outcomes, Tool Use, and Steering. Together with the Alignment Index, these indexes provide a comprehensive view of how agents perform across real-world tasks, from completing complex workflows to using tools and adapting to user feedback. Arena measures agentic performance from millions of real-world tasks by our global community. With the launch of the new indexes, we are updating our scores to provide a more stable and interpretable way to understand how agents perform in the real world. Claude Fable 5.2 (Max) leads the Agent Arena Index by 134 points with a score of 1463. Top 5 labs on the Agent Arena Index: - #1 @AnthropicAI : With Claude Fable 5.2 (Max) at 1463 pts - #2 @GoogleDeepMind : With Gemini 4 Carbon (High) at 1307 pts - #3 @OpenAI : With GPT-6 Astra (Max) at 1274 pts - #4 @AIatMeta : With Muse Wonder Full (Max) at 1200 pts - #5 @Alibaba_Qwen : With Qwen4-Max (xHigh) at 1191 pts The Agent Arena Index combines four key signals of real-world agent performance: - Task Completion: explicit confirmation of task success from users - Praise vs. Complaint: user satisfaction with agent's outcome - Bash Reliability: how well an agent uses terminal tools - Steerability: how well an agent responds to user corrections Alongside capability, the Alignment Index measures how faithfully agents act in accordance with user intent, based on three key signals: Deceptive Completion, Unauthorized Action, and False Attribution. As agents take on increasingly complex, long-horizon work, measuring their real-world capabilities and alignment is more important than ever. Explore the rankings and see what each index measures in the thread below.
本条情报归属 AITOP「模型」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「中美大模型技术代差与商业化对照」「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Agent Arena Index、Claude、Gemini、GPT-6,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「lmarena.ai」(@lmarena_ai),经 AITOP 多维评分管线结构化提炼。