Cisco Foundation AI has introduced Antares, a new family of open-weight small language models designed specifically for vulnerability localization in code. The models, Antares-350M and Antares-1B, are available on Hugging Face and are based on IBM Granite 4.0 checkpoints. Alongside the models, Cisco has released the Vulnerability Localization Benchmark (VLoc Bench) to evaluate their performance. While not achieving state-of-the-art results compared to larger models like GPT-5.5, Antares-1B demonstrates strong performance for its size, outperforming larger open-weight models and traditional static analysis tools in identifying vulnerable files. AI
IMPACT Provides specialized models for code security, potentially improving developer efficiency in identifying vulnerabilities.
RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=2 ai=1.0]
- Antares
- Antares-1B
- Antares-350M
- Apache Software License 2.0
- Cisco Foundation AI
- Common Weakness Enumeration
- Gemini 2.5 Flash
- Gemma-4-31B
- GitHub Security Advisories
- GLM-5.2
- GPT-5.5
- Hugging Face
- IBM Granite 4.0
- VLoc Bench
- Vulnerability Localization Benchmark
- Cisco
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
