MarkTechPost2 Min Read

Cisco Foundation AI Releases Antares: 350M and 1B Open-Weight Models That Localize Known Vulnerabilities Inside Real Codebases

M

MarkTechPost

7/22/2026

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 .

Strategic AI Brief

Impact Analysis

Cisco Foundation AI has released Antares, a family of small language models trained to pinpoint where known vulnerabilities live inside a codebase.

Market Signal

Antares-1B reaches 0.209 File F1 on the new Vulnerability Localization Benchmark, above GLM-5.2 at 753B parameters and Gemini 3 Pro.

Tactical Warning

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 .

Share this insight: