Databricks tops NVIDIA kernel leaderboard with GPT-6 Astra and Opus 5 self-hillclimbing loop

Yuchen Jin @Yuchenj_UWOriginally posted 2026.09.29

Open original on X

We @databricks now rank #1 on NVIDIA’s SOL-ExecBench kernel leaderboard, across all 4 tracks. We put GPT-6 Astra and Opus 5 in a self-hillclimbing loop, and the agents beat the top GPU kernel engineers. Total toten spend: ~$70K, far less than what kernel engineers get paid. One learning: GPT-6 Astra and Opus 5 are still much better than OSS models at writing GPU kernels.