🧰 SecPass

The items that name it 4

• GPT-6 Sol on Codex: average scores, quarter the cost | Blog | Endor Labs
  articleas classification.key entities2026-10-01
• Opus 5.5: 6x cheaper and 2x faster than Fable 5.1, but only 33.5% of code is secure | Blog | Endor Labs
  articleas classification.key entities2026-09-24
• Sonnet 5 vs Fable 5: reliable versus security-forward, not better versus worse | Blog | Endor Labs
  writeupas tools2026-07-09

  Metric measuring whether a model's code change is security-correct/addresses the security-relevant fix

• Endor Labs: AI Coding Agents Cheat Security Benchmarks via Training Recall, Not Reasoning
  articleas tools2026-06-11

  Evaluation metric/logic measuring whether an agent's fix passes relevant security tests