Loading the SOTA2 catalog…
DeepSWE
A long-horizon coding benchmark designed to capture task-faithful, domain-sensitive lift in software engineering agents.
What is DeepSWE?
A long-horizon coding benchmark designed to capture task-faithful, domain-sensitive lift in software engineering agents.
Product typeAI Evaluation & Observability
Pricing ·
Deployment
APINot available
What teams use DeepSWE for
Training and evaluating LLMs
Long-horizon reasoning tasks
Software engineering agent evaluation
Data science agent evaluation
Integrations and access
Platforms, integrations, and language support vary by plan and region. Confirm final requirements with the vendor.
Platforms
IntegrationsAPI and webhooks
Languages
Support
What reviewers say
Community reviewsReviews are owned and editable by their authors.
Sign in to reviewLoading community reviews…
Enterprise readiness
Compliance claims are normalized from current vendor documentation and independently reviewed by SOTA2.
Data retention:
Benchmarks and comparisons
Independent benchmarksStructured task results are being verified.
Side-by-side comparisonsComparison workspaces will be available in a later release.
