evals.report
BenchmarksLabsCompareRun guides
Models
1 selected
Nex-N2-ProNex AGI
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
BenchmarkNex-N2-ProNex AGI
SWE-bench Verified% resolved80.8%
DeepSWE% resolved33.6%
SWE-bench Pro% resolved58.8%

No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.