DeepSWE A
AI benchmark · Coding
What is DeepSWE?
DeepSWE measures frontier coding agents on 113 original, long-horizon software engineering tasks across 91 open-source repositories in five languages, graded by hand-written behavioral verifiers.
Coding mostly
“DeepSWE is a long-horizon software engineering benchmark that delivers four major advances over today's public benchmarks”
deepswe.datacurve.ai/blog/deepswe ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Derived benchmarks
DeepSWE 1.1 later version
Included in
Artificial Analysis Coding Agent Index
“An Artificial Analysis aggregate index scoring coding agents on end-to-end software engineering tasks, combining DeepSWE, Terminal-Bench and SWE-Atlas-QnA.”
Tier A
Widely used: a lab reports it, or 50 or more models are scored 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.
- 27 models scored
- listed with Datacurve
- in curated RL directories (7 pts)
- its family includes DeepSWE 1.1 (tier S)
On X · well regarded, moderate buzz, from 9 posts about DeepSWE in the last month
DeepSWE v1.1 shows up routinely in model cards and launch posts as the measure of long-horizon coding, with little criticism of the benchmark itself.
How we got to tier A
- Adoption: 27 models scored; listed with Datacurve. Tier B.
- On X: well regarded, moderate buzz. “DeepSWE v1.1 shows up routinely in model cards and launch posts as the measure of long-horizon coding, with little criticism of the benchmark itself.” No move.
- In curated RL directories: 7 points, a floor of B.
- Root of a benchmark family that includes DeepSWE 1.1 (tier S): raised to A, one step below.
- 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 DeepSWE 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.