Matrix Multiplication GPU Kernel Synthesis on KernelBench (test)
1.16Square MatMul ScoreCuTeGen
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CuTeGenGPU=NVIDIA GeForce RTX 4090 (24 GB), CUDA version=13.0, PyTorch version=2.8.0, CUTLASS version=v4.3.0 (commit acb4593), LLM Engine=GPT-5, Evaluation Protocol=Relative to PyTorch reference implementation2026.04 | 1.16 | 0.67 | 0.53 | 0.86 | 1.02 | 0.81 | 0.98 | 0.82 | 0.71 | 1 | 0.43 | 17.66 |