About KernelBench Hard H100
Definition and scoring
- Organisation
- Elliot Arledge
- Category
- Coding
- Version
- 2026
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Unknown
An agentic GPU-kernel benchmark that measures how much of the hardware roofline a model's correct, audit-clean kernels reach on six demanding CUDA and Triton problems. Every genuine source row stays tied to its exact model label, configuration, benchmark version and evaluation system. The summary chart shows one best compatible score per canonical product; Score 2.0 admits only explicitly mapped, frozen protocols and keeps incompatible configurations separate.
Open benchmark source ↗