KernelBench Mega B
AI benchmark
- Built by
- Elliot Arledge
- Tier
- B why
- Snapshot
What is KernelBench Mega?
KernelBench Mega measures whether coding agents can write a single fused GPU megakernel (e.g., Kimi-Linear W4A16 batch-1 decode) and how much speedup it achieves over an optimized PyTorch baseline.
Coding mostly
“Claude Fable 5 [max] wrote the first genuine (and fastest) megakernel ever submitted to KernelBench-Mega.”
x.com/elliotarledge/status/2072814573753975266?lang=en ↗
Who built KernelBench Mega
Led by Elliot Arledge.
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
KernelBench original
Tier B
Established: 15 or more models scored, or curated RL directories rate it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 29 models scored
- in curated RL directories (1 pt)
How we got to tier B
- Adoption: 29 models scored. Tier B.
- On X: unclear, none buzz No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where KernelBench Mega sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-10 snapshot.