Primary sourceArtificial Analysis
View sourceEvent ·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 sourcesRelated source 1TestingCatalog
View sourceRelated source 2karminski-牙医 (AI工具)
View sourceRelated source 3Bindu Reddy
View sourceRelated source 4kimmonismus
View sourceRelated source 5IT之家
View sourceRelated source 6Teortaxes
View sourceRelated source 7Noam Brown (OpenAI 推理)
View sourceRelated source 8Latent Space (swyx)
View sourceRelated source 9techcrunch
View sourceRelated source 10rohanpaul_ai
View sourceConflict 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.