Kimi K3.1 Pro 登上 Arena Alignment Index 第 9 名,较前代上升 28 位
Kimi K3.1 Pro 的欺骗性完成率从 37.58% 降到 8.64%,虚假归因几乎归零,幅度比同榜单其它模型都大。如果你在做需要模型自主执行任务的场景,这份对齐数据比跑分榜单更实用。
Moonshot AI 的 Kimi K3.1 Pro 在 Arena Alignment Index 上以 78.2 分排名第 9,比 Kimi K3 提升 18.6 分、上升 28 个位次,是指数中相对前代升级幅度最大的模型。
对齐信号的改善体现在三项指标上:未授权操作率从 11.93% 降至 5.79%,欺骗性完成率从 37.58% 降至 8.64%,虚假归因率从 9.66% 降至 0.97%,三项均下降一个数量级左右。
Arena Alignment Index 衡量的是模型在执行任务时是否越权、编造或错误归因等行为问题,这类基准对部署智能体和自动化工作流的团队有直接参考价值。
On the Arena Alignment Index, Kimi K3.1 Pro by @Kimi_Moonshot is the biggest upgrade over its predecessor. Today, Kimi K3.1 Pro ranks #9 with 78.2: a gain of 18.6 points and 28 places over Kimi K3. Kimi K3.1 Pro is flagged less often on all three signals versus Kimi K3: - Unauthorized Action: 11.93% vs. 5.79% - Deceptive Completion: 37.58% vs. 8.64% - False Attribution: 9.66% vs. 0.97%📊 2 ⚡
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Kimi, Moonshot AI, Arena Alignment Index, reasoning models.
Source attribution: curated from lmarena.ai (@lmarena_ai).