Glossary · Term

SWE-bench

← all terms

Definition

Plain language

A benchmark that tests AI agents on real bug-fixing tasks pulled from open-source GitHub projects.

As stated in the literature

A benchmark of real-world GitHub issues from popular Python projects paired with held-out tests, used to evaluate autonomous coding agents end-to-end.

Also called: SWE-bench Verified

Why it matters: It tests coding agents on the messy, real-world software work they're being marketed for, rather than on toy programming puzzles.

For example, an agent might be given a real Django bug report and asked to produce a patch that passes the maintainers' actual test suite.

Heard on the show

“It's a measured, named, quantified habit across every leading coding model on the SWE-bench leaderboard.”
Episode 232 — Coding Models Can Find the Bad Line, They Just Won't Delete It

Mentioned in 10 episodes

  1. 232
    Coding Models Can Find the Bad Line, They Just Won't Delete It
  2. 195
    Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does
  3. 147
    Agents Fail at the Body, Not the Brain: A Self-Rewriting Scaffold That Lifts a 9B Model 44 Points
  4. 142
    Training a Tiny Model to Run the Plumbing Between an Agent and the World
  5. 130
    Why AI Agents Coordinate Better Through a Shared Board Than a Boss
  6. 126
    How Coding Agents Can Mine Their Own Failures Into a Self-Targeting Curriculum
  7. 093
    A Calibrated Knob for Weak-to-Strong AI Oversight, Tested on Real Code
  8. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
  9. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
  10. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger

Related concepts

Related terms