MLPerf Edge Agentic Inference
Multi-turn agentic tasks (e.g. coding) on edge devices with an edge model and quantization; model not named
v6.1efficiencyactive
Definition
- Version
- v6.1
- Category
- efficiency
- Maintainer
- MLCommons
- Status
- active
- Home page
- https://mlcommons.org/benchmarks/inference-edge/
Sources
- MLCommons Sets Participation Record with New MLPerf Inference v6.1 Benchmark Results | FinancialContent financialcontent.com https://www.financialcontent.com/article/gnwcq-2026-9-16-mlcommons-sets-participation-record-with-new-mlperf-inference-v61-benchmark-results
- Benchmark MLPerf Inference: Edge | MLCommons V6.1 Results mlcommons.org https://mlcommons.org/benchmarks/inference-edge/
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 Edge Agentic Inference", https://aurion.semai.id/benchmarks/mlperf-inference-edge-agentic/, records of October 2026.