SWE-bench Verified
SWE-bench Verified: every model scored on it, ranked, with a source on every score, and the current models not yet covered.
- Models scored
- 110 models
- Unit
- percent
- Tier
- core
- Share of the intelligence index
- 15.9%
SWE-bench Verified: every model scored on it, ranked, with a source on every score, and the current models not yet covered.