arena.ai 推出 Agent Arena Index 智能体排行榜
Check out the NEW Agent Arena Index: https://t.co/sE9q4FSYAt and learn more about the new Coding Ind...
arena.ai 新上了智能体榜单,用数百万真实任务打分。Anthropic 的 Claude Fable 5.2 拿了第一,比 Gemini 4 Carbon 高 134 分。做智能体开发或者选型的人可以直接查各家的细分成绩,比看跑分有参考价值。
arena.ai 发布 Agent Arena Index,作为衡量智能体综合表现的旗舰指标,并新增 Agentic Work、Coding、Chat、Task Outcomes、Tool Use、Steering 六个细分指数,与既有 Alignment Index 一起构成完整评估体系。榜单基于全球社区数百万真实任务的数据打分。
排名方面,Anthropic 的 Claude Fable 5.2 (Max) 以 1463 分居首,领先第二名 134 分;Google DeepMind 的 Gemini 4 Carbon (High) 得 1307 分排第二,OpenAI 的 GPT-6 Astra (Max) 以 1274 分列第三,Meta 的 Muse Wonder Full (Max) 和阿里 Qwen4-Max (xHigh) 分列四五位。
Agent Arena Index 综合四项信号:任务完成的用户确认、赞美与投诉比例、Bash 终端工具使用可靠性,以及对用户纠正的响应能力(Steerability)。Alignment Index 则通过 Deceptive Completion、Unauthorized Action、False Attribution 三项信号衡量智能体是否忠实执行用户意图。
Check out the NEW Agent Arena Index: https://t.co/sE9q4FSYAt and learn more about the new Coding Ind...
Check out the NEW Agent Arena Index: arena.ai/leaderboard/ag… and learn more about the new Coding Index below x.com/arena/status/2… Arena.ai @arena 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「产品」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「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、Anthropic、Claude、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。截至目前,全网已有 11 家独立信源对该事件进行交叉印证与跟进报道(含 Artificial Analysis、Rowan Cheung、rohanpaul_ai 等),属于近期高关注度行业信号。