Databricks Tops All 4 NVIDIA SOL-ExecBench Kernel Tracks Using AI Agents for ~$70K
Yuchenj_UW · x · 2026-09-29
Databricks claims the #1 spot on NVIDIA's SOL-ExecBench GPU kernel leaderboard across all 4 tracks.
- Method: GPT-6 Astra and Opus 5 were run in a self-hillclimbing loop; the agents produced kernels that beat top GPU kernel engineers
- Cost: total token spend was roughly $70K, far below kernel engineer salaries
- Takeaway: GPT-6 Astra and Opus 5 remain substantially better than open-source models at writing GPU kernels
More from coding & agent
- Community-maintained list tracks 51 active AI angel investors with sources and verification dates — TheMoonMidas · 2026-09-29
- px0 release fixes LSP memory leaks, ReDoS vulnerability, adds CSV table rendering — arpit_bhayani · 2026-09-29
- Local gamedev AI stack: Meta's Muse Glimmer nails tool use in one try where Gemma 4 12b fails — draginol · 2026-09-29
- Founder: AI Can Now Do the Work of 10 Employees Before You Hire — FinanceYF5 · 2026-09-29
- Univer open-sources an Office SDK for AI agents: spreadsheets, docs and slides in one runtime — abhishek__AI · 2026-09-29
- Gamers are using Opus 5.5 to rewrite entire games in Rust and merge them together — Promptmethus · 2026-09-29