Event ·Multi-source

Kimi K3.1 Pro 登顶 Artificial Analysis 网络防御开源模型榜首

Moonshot 的 Kimi K3.1 Pro 在 Artificial Analysis Cyber Index 上得分 64%,成为排名第一的开放可用模型,领先 DeepSeek V4.1 Flash 1017(57%)7 分,仅次于 OpenAI 受限访问的 GPT-6 Sol(Daybreak Blue,69%)。相比 Kimi K3 的 41%,K3.1 Pro 提升 23 分,并在 CyberGym-E2E-AA 上以 95% 超过 GPT-6 Sol(93%)。该指数由 CWE-Bench-AA、DeepsecBench-AA 和 CyberGym-E2E-AA 三个基准组成,衡量智能体网络防御能力。成本方面,K3.1 Pro 的单任务成本为 2.81 美元,虽代币价格比 Kimi K3 便宜 33%,但因输入 token 翻倍反而高出 15%。

Current read

Moonshot 的 Kimi K3.1 Pro 在网络防御基准拿了开源模型第一,CyberGym-E2E-AA 得分 95% 连 GPT-6 Sol 都被超过,不过单任务成本反而变贵了,这篇把各家分数和价格都列得很清楚。

11 sources71° AI heatLast updated 2026/10/23 22:51:18

Evidence

11 sources
Primary sourceArtificial Analysis
View source
Related source 1TestingCatalog
View source
Related source 2karminski-牙医 (AI工具)
View source
Related source 3Bindu Reddy
View source
Related source 4kimmonismus
View source
Related source 6Teortaxes
View source
Related source 7Noam Brown (OpenAI 推理)
View source
Related source 8Latent Space (swyx)
View source
Related source 9techcrunch
View source
Related source 10rohanpaul_ai
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.