News for hackers. Stuff that matters.

A comment on Benchmarking Coding Agents on Databricks' Multi-Million Line Codebase.

Re:Benchmarking Coding Agents on Databricks' Multi-Million L... by yigitcan07 on Thursday July 09, 2026 @04:50AM (#48842884)
Would be great to see time spent per task per model. Especially since article references 390+ tokens per second for GLM5.2.
[ Parent | on HN ]

There are no comments on this comment yet.