Benchmark
SWE-Bench Pro Verified
What is SWE-Bench Pro Verified?
A verified version of SWE-Bench Pro for evaluating software engineering agents on repository-level coding tasks.
- Released
- 2026-09-08
- Evaluates
- Code, Code & Software, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.08149
SWE-Bench Pro Verified paper
No reported scores are on record for this benchmark yet.