KernelBench
A GPU kernel auto-generation and evaluation benchmark proposed by Meta, designed to measure the capability of large language models to automatically generate high-performance GPU kernels. It serves as a key evaluation tool in AI-assisted GPU programming research.
Timeline (last 90 days)
On KernelBench (low-level GPU code writing), DeepSeek C.E Flash 1017 ranks third, behind only the latest Claude model, but beats Gemini 4 Argon, Claude Fable and GPT Leo Astra.
Meta's KernelBench and related research from institutions such as DeepMind have attempted to use LLMs to automatically generate and evaluate GPU kernels
All Facts (2)
On KernelBench (low-level GPU code writing), DeepSeek C.E Flash 1017 ranks third, behind only the latest Claude model, but beats Gemini 4 Argon, Claude Fable and GPT Leo Astra.
50%UnverifiedMeta's KernelBench and related research from institutions such as DeepMind have attempted to use LLMs to automatically generate and evaluate GPU kernels
50%