Development

A software benchmark ships contamination-free repos and behavioral verifiers

development2026-05-28

Claim

Datacurve launched DeepSWE, a long-horizon software engineering benchmark with 91 contamination-free repos across 5 languages, solutions 5.5 times denser than SWE-bench Pro, and hand-written behavioral verifiers.

Reported metric: 91 repos / 5.5x density

Reporting date: 2026-05-28 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to May 28, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to May 28, 2026

Actor

Datacurve

Evidence for

Supersedes

A benchmark spans twenty-three real deployable SaaS systems

Referenced by

Cite or correct this record

Citation formatCitation text

A software benchmark ships contamination-free repos and behavioral verifiers
Innermost Loop KB — secondary record
Reporting date: 2026-05-28
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-05-28-a-contamination-free-software-benchmark
Claim: Datacurve launched DeepSWE, a long-horizon software engineering benchmark with 91 contamination-free repos across 5 languages, solutions 5.5 times denser than SWE-bench Pro, and hand-written behavioral verifiers.
Attributed sources:
- Welcome to May 28, 2026 — https://theinnermostloop.substack.com/p/welcome-to-may-28-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.