🧰 Agent Security League

The items that name it 9

• ADLC metrics: How to measure agentic development security | Endor Labs
  articleas classification.key entities2026-10-29
• Gemini 4 Argon on Cursor: solid security score, two unique solves, but slower and more expensive | Endor Labs
  writeupas frameworks and tools2026-10-20

  Endor Labs public leaderboard of coding agent and model combos scored on security of generated code.

• Sonnet 5 vs Fable 5: reliable versus security-forward, not better versus worse | Endor Labs
  writeupas frameworks and tools2026-10-12

  Endor Labs evaluation running AI coding models with two agent harnesses on the same 200-task dataset, scoring FuncPass and SecPass

• Is AI Coding Safe? Introducing the Agent Security League | Blog | Endor Labs
  articleas frameworks and tools2026-10-12

  Independent, open public leaderboard from Endor Labs tracking security of commercial coding agents and models using SusVibes

• Opus 5.5: 6x cheaper and 2x faster than Fable 5.1, but only 33.5% of code is secure | Blog | Endor Labs
  writeupas classification.key entities2026-09-25
• Claude Code with Fable 5.1 posts 87.2% FuncPass and 37.4% SecPass — a new #1 on our board — while running as fast as Fable 5, costing a third of Opus 5, finishing every task with zero timeouts, and drawing less than half the confirmed cheating of both predecessors. | Blog | Endor Labs
  articleas classification.key entities2026-09-04
• OpenAI Codex with GPT-5.6 Sol: competitive, zero cheating, one unique Django fix | Blog | Endor Labs
  writeupas frameworks and tools2026-07-17

  Endor Labs benchmark of coding agent and model combos on real-world coding tasks, measuring FuncPass and SecPass

• Everyone Wins Their Own Benchmark | Blog | Endor Labs
  articleas frameworks and tools2026-07-14

  Ongoing Endor Labs benchmark of how coding agents handle security

• Claude Sonnet 5 with Cursor: strong reasoning, throttled by the harness | Blog | Endor Labs
  articleas classification.key entities2026-07-09

In every workspace you can read 28