SWE-bench Verified S
AI benchmark · Coding
What is SWE-bench Verified?
SWE-bench Verified measures whether AI models can resolve real-world GitHub issues by generating patches that pass unit tests, using 500 human-validated samples from Python repositories.
Coding mostly
“We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.”
openai.com/index/introducing-swe-bench-verified/ ↗
Who built SWE-bench Verified
Led by OpenAI, with the SWE-bench authors (Princeton).
Paper: arxiv.org/abs/2310.06770 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
SWE-bench original
Derived benchmarks
SWE-bench Verified Extended extension
SWE-bench Verified Mini subset
Tier S
The standard: frontier labs report it, or a trusted evaluator scores hundreds of models on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 72 models scored
- reported by OpenAI
- in curated RL directories (2 pts)
On X · mixed, moderate buzz, from 12 posts about SWE-bench Verified in the last month
Still the default coding score cited for open models and tools, but people note saturation, contamination, and OpenAI dropping it in favor of newer benchmarks.
How we got to tier S
- Adoption: 72 models scored; reported by OpenAI. Tier S.
- On X: mixed, moderate buzz. “Still the default coding score cited for open models and tools, but people note saturation, contamination, and OpenAI dropping it in favor of newer benchmarks.” No move.
- In curated RL directories: 2 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where SWE-bench Verified sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.