FrontierSWE

FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. Performance is reported as a dominance score, where higher is better.

Released

Unknown

Readiness

Paper only

Primary field

General AI

Benchmark Radar records only publicly supported details and links back to primary sources for verification.