Matrix Multiplication on CUDA-LLM kernels task suite 1.0 (test) benchmark leaderboard · SOTA2 Research

Matrix Multiplication on CUDA-LLM kernels task suite 1.0 (test)

4.4Execution TimeOptiML

Evaluation Results

Method	Links
OptiML2026.02		4.4	1.64	81.17	11.03	92.61	70	282	381	95.58	44
HPC-Coder-V2 + OptiML-X2026.02		4.52	1.59	79.16	10.86	92.21	73	286	386	95.44	44
GPT 5.1 + OptiML-X2026.02		4.62	1.56	78.41	10.62	92.07	79	292	392	95.27	44
StarCoder2 + OptiML-X2026.02		4.74	1.52	77.42	10.33	91.63	77	301	395	95.01	46
Qwen2.5-Coder + OptiML-X2026.02		4.98	1.45	76.58	10.14	91.22	74	318	400	94.83	46
GPT 5.12026.02		7.2	—	71.26	8.42	91.36	63	408	419	95.14	44
Qwen2.5-Coder2026.02		7.65	0.94	69.4	8.1	90.98	66	421	432	94.62	46
HPC-Coder-V22026.02		7.88	0.91	68.72	8.02	90.71	67	427	438	94.31	46
StarCoder22026.02		8.23	0.87	67.95	7.92	90.41	68	435	441	93.97	48