Cybersecurity
ExploitGym
Published per-task on-target verdicts for five ExploitGym agent submissions, retaining mitigation profiles and the additional two-hour result view.
1,737items
5subjects
Framework code: Apache-2.0. Task data retain their upstream licenses, as documented in DATA_LICENSE.md (including GPL-2.0, BSD-3-Clause and project-specific terms). The results repository does not declare a separate license. No blanket Apache license is asserted for redistributed data.license
cybersecuritydomain
software_engineeringdomain
agents_and_tool_usedomain
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect