思科开源了超小的漏洞定位模型 Antares，比 GPT-5.5 快几百倍还便宜，代码安全工程师可以试试。
Cisco Foundation AI 发布了 Antares 系列开源权重模型，包括 350M 和 1B 参数两个版本，用于在真实代码库中定位已知漏洞。Antares-1B 在全新的 Vulnerability Localization Benchmark 上达到 0.209 File F1，超过 753B 参数的 GLM-5.2 和 Gemini 3 Pro。未经过后训练的 Granite 4.0 基准得分为接近零，表明几乎所有能力来自后训练阶段。在单张 H100 上运行 500 个任务仅需约 13 分钟，成本低于 1 美元，而 GPT-5.5 完成相同任务需 141 美元。
Cisco Foundation AI Releases Antares: 350M and 1B Open-Weight Models That Localize Known Vulnerabilities Inside Real Codebases
Cisco Foundation AI has released Antares, a family of small language models trained to pinpoint where known vulnerabilities live inside a codebase. Antares-1B reaches 0.209 File F1 on the new Vulnerability Localization Benchmark, above GLM-5.2 at 753B parameters and Gemini 3 Pro. The untrained Granite 4.0 checkpoints score near zero under the same protocol, so post-training supplies almost all of the capability. A full 500-task sweep runs in roughly 13 minutes on a single H100 for under a dollar, against $141 for GPT-5.5. The post Cisco Foundation AI Releases Antares: 350M and 1B Open-Weight Models That Localize Known Vulnerabilities Inside Real Codebases appeared first on MarkTechPost .