MLPerf Inference v6.0

Audited MLCommons inference benchmark results for datacenter, edge, and GenAI workloads, including throughput, latency, and power-efficiency views.

2rows
offline_throughputprimary metric
2026-05-27sampled

Metadata

ID
mlperf_inference_v6
Category
Inference
Release
Unknown

Metrics

Offline Throughput, Server Throughput, Interactive Throughput, ROUGE1, ROUGE2, ROUGEL

Latest Results

Compact import from one public MLCommons summary.html. Full repository contains many vendor/system submissions and should be expanded with a dedicated parser.

Rank Subject Offline Throughput Model Match Provenance Sampled
1 AMD 87xMI355X llama2-70b-99 1042110 Tokens/s — Imported 2026-05-27
2 AMD 87xMI355X llama2-70b-99.9 1042110 Tokens/s — Imported 2026-05-27