Yuchen Jin· @Yuchenj_UW · X·· 2 天前AI 评分54
AI 导读
Databricks 团队在 NVIDIA SOL-ExecBench 内核排行榜的全部 4 个赛道排名第一。作者称他们把 GPT-6 Astra 和 Opus 5 放入自我爬坡循环，智能体表现超过顶级 GPU 内核工程师，总 token 花费约 $70K，且这两个模型在写 GPU 内核上仍明显强于开源模型。
正文
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.
来源：Yuchen Jin · x.com