Coding and terminal agents / Benchmark leaderboard
SWE-bench Pro
Long-horizon repository-level software tasks; public Harbor snapshot has 731 tasks.
No published company result yet.
This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.
Arrange an evaluation for your company →What this benchmark measures
Metrics
Resolved-task rate.
Execution requirements
Repository agent and Pro-specific environments/tests.
Scope and limitations
Use the public split identity; do not treat Pro, Verified and private commercial evaluations as interchangeable.
Evaluation availability
Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.
Sources and company fit
- Original benchmark ↗Established newer suite
- Hugging Face · ScaleAI/SWE-bench_Pro ↗Public · Selected repository-level coding suite.
Companies whose products may fit
Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.
Compatibility notes for each company
All Hands / OpenHands: Capability-aligned; adapter/access to qualify
Augment Code: Capability-aligned; adapter/access to qualify
Cline: Capability-aligned; adapter/access to qualify
Cognition / Devin: Capability-aligned; adapter/access to qualify
Cursor: Capability-aligned; adapter/access to qualify
Factory: Capability-aligned; adapter/access to qualify
GitHub Copilot: Capability-aligned; adapter/access to qualify
JetBrains: Capability-aligned; adapter/access to qualify
Replit: Capability-aligned; adapter/access to qualify
Sourcegraph: Capability-aligned; adapter/access to qualify