Hacker News new | past | comments | ask | show | jobs | submit

Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases

https://withspecific.com/benchmarks/real-swe
loading story #49679794
loading story #49677907
loading story #49679705
loading story #49677623
loading story #49677769
loading story #49678527
loading story #49677656
loading story #49678171
loading story #49677912
loading story #49679624
loading story #49678166
loading story #49679143
loading story #49679790
loading story #49677549
loading story #49677329
loading story #49679403
loading story #49677355
loading story #49678257
loading story #49677445
loading story #49678750
loading story #49677452
loading story #49677552
loading story #49679640
loading story #49678495
loading story #49678863
loading story #49677705
loading story #49677544
loading story #49677618