KernelGenBench-MC (Claude Code) - Platform B: leaderboard

Metric: Clean pass rate (%; share of the 110 PyTorch ATen operators whose generated Triton kernel passes numerical validation on every test case of its combinatorial shape, dtype and layout suite and every anti-hack check, as a drop-in replacement; the Claude Code agent with execution feedback; de-identified Platform B; 30-minute budget per operator). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.

Top models

#ModelScore
1Claude Opus 4.696
2MiniMax-M2.583
3Qwen 3.5 27B82
4GLM-559

Interactive version: theaggregate.ai/benchmark?slug=kernelgenbench-mc-claude-code-platform-b · How It Works · Data refreshed daily, snapshot 2026-09-29.