MLPerf Inference
Throughput and latency at a quality target; Sep 2025 round added Llama 3.2 1B and 3B for edge
v5.1efficiencysuperseded
Definition
- Version
- v5.1
- Category
- efficiency
- Maintainer
- MLCommons
- Status
- superseded
- Home page
- not in the notes
Sources
- Mlperf Inference V5 1 Results winzheng.com https://www.winzheng.com/en/article/mlperf-inference-v5-1-results
Scores
The notes record no score on this benchmark.
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MLPerf Inference", https://aurion.semai.id/benchmarks/mlperf-inference-v5-1/, records of October 2026.