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
Related event: Databricks Tops NVIDIA Kernel Leaderboard with AI Agents(2 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16