evaluation-family · Source-linked discovery
Swe Bench Verified Mini
Evaluates AI's ability to resolve genuine software engineering issues sourced from 12 popular Python GitHub repositories, reflecting realistic coding and debugging scenarios.
OriginCarlos E. Jimenez, John Yang, Alexander Wettig et al.TopicsGeneral capabilityStatusimported
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.