KernelBench Hard

KernelBench Hard evaluates agentic GPU kernel optimization on the hardest problem set. Each question is scored by the agent's submitted operator TFLOPs relative to the theoretical peak of the current hardware, with the benchmark score being the average across all questions.

Released

Unknown

Readiness

Paper only

Primary field

General AI

Benchmark Radar records only publicly supported details and links back to primary sources for verification.