โ Fleet-evaluation harness for security-agent benchmarks ๐๐๐ฏ๐ฒ๐ฟ๐๐๐บ-๐๐ฎ๐, ๐๐ ๐ฝ๐น๐ผ๐ถ๐๐๐๐บ, ๐๐ ๐ฝ๐น๐ผ๐ถ๐๐๐ฒ๐ป๐ฐ๐ต ๐ฉ๐ด, ๐๐ฉ๐-๐ฏ๐ฒ๐ป๐ฐ๐ต, run in real disposable sandboxes per trial โ with Modal-based KVM-capable sandboxes planned for kernel-exploit tasks. Measures agent capability and infra reliability, with Langfuse monitoring.
-
Updated
Nov 5, 2026 - Python