KernelGenBench-MS (Claude Code) - ATen Operators: 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; NVIDIA A100; 30-minute budget per operator). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.

Top models

#ModelScore
1Claude Opus 4.692
2Qwen 3.5 27B80
3GLM-572
4MiniMax-M2.569

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