01:30
2026-06-29
runtimewire.com
ai-research
Semgrep says GLM 5.2 beat Claude in a narrow security benchmark
Semgrep co-founders Isaac Evans, Drew Dennison and Luke O'Malley published a benchmark on June 22 showing that Zhipu AI's open-weight model GLM 5.2 scored 39% F1 on an IDOR vulnerability-detection tesβ¦