← The AI Systems Map
L0 · LabsBenchmark / eval

MLPerf (MLCommons)

The industry-standard training & inference benchmark

MLPerf, run by the MLCommons consortium, is the neutral benchmark suite for training and inference performance across Nvidia, AMD, Google TPU, Intel, and neocloud submitters, and is the reference buyers cite for silicon comparison. It anchors hardware marketing claims and procurement. MLCommons also stewards safety and data benchmarks like AILuminate.

Body

MLCommons

Scope

Training + Inference

How it fits the stack

MLPerf (MLCommons) with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

usesusesMLPerf (MLCommons)LabsGoogle TPUNvidia Data-Center GPU(Blackwell/Rubin)chokepoint
MLPerf (MLCommons)Depends on ↑

MLPerf (MLCommons) in the AI stack. MLPerf (MLCommons) with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 3 entities, 2 relationships
  • MLPerf (MLCommons)usesGoogle TPU
  • MLPerf (MLCommons)usesNvidia Data-Center GPU (Blackwell/Rubin)