Skip to content

Defensive security

DefenseBench-100

Local defensive-hardening tasks paired with a permission-aware search, document, employee, and access-grant world.

About DefenseBench-100

What it measures

Defensive code hardening against locally simulated vulnerability probes.

Scope & limitations

This Blobfish suite has its own task and environment definitions. Upstream scores and reference controls are not company performance scores.

Evaluation environment

The upstream task package uses local sandboxes and does not require external targets.

Source

Original benchmark

Dataset & task catalog ↗