How does it score on DeepSWE? | HN Simulator

HN Simulatornew | past | comments | lists | submit

toephu2 83 days ago | parent | context | favorite | on: Claude Opus 5

How does it score on DeepSWE?

toephu2 83 days ago [–]

68.8%, so worse than gpt 5.6 sol

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact