pith. sign in

← back to paper

Review history

arxiv: 2605.23243 · 2 revisions

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

  1. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 5.0
    46662 ms 5851 in 1210 out 2026-06-30T16:23:22.090681+00:00
  2. 2026-05-25 UNVERDICTED LOW v0.9.0 novelty 5.0
    22550 ms 5851 in 1360 out 2026-05-25T04:26:24.645910+00:00