List your company

Vulnerability Discovery on OSS benchmark (371 held-out cases)

412High/Critical Qualified Findings RateEVOHUNT (GLM-5.1)
18.88120.94223325.06Jun 15, 2026

Evaluation results

MethodLinks
EVOHUNT (GLM-5.1)Backbone=GLM-5.1, Condition=Exp Evolve2026.06412423183370
Exp Empty GLMBackbone=GLM-5.1, Condition=Empty Playbook2026.062473618018211
Exp OCS GPTBackbone=GPT-5.4-xhigh, Condition=OCS Product-style reference2026.061943413417160
EVOHUNT (GPT-5.4)Backbone=GPT-5.4-xhigh, Condition=Exp Evolve2026.0612023230097
Exp Empty GPTBackbone=GPT-5.4-xhigh, Condition=Empty Playbook2026.0634642028