Open Source Continuous Inference Benchmark trusted by Operators of Trillion Dollar GigaWatt Scale Token Factories
As the world progresses exponentially towards AGI, software development and model releases move at the speed of light. Existing benchmarks rapidly become obsolete due to their static nature, and participants often submit software images purpose-built for the benchmark itself which do not reflect real world performance.
InferenceX™ (formerly InferenceMAX) is our independent, vendor neutral, reproducible benchmark which addresses these issues by continuously benchmarking inference software across a wide range of AI accelerators that are actually available to the ML community.
Our open data & insights are widely adopted by the ML community, capacity planning strategy teams at trillion dollar token factories & AI Labs & at multiple billion dollar NeoClouds. Learn more in our articles: v1, v2.
GPU Reliability
Success rate percentages for inference runs across GPU models, showing hardware reliability for inference runs over time.
Success Rate by GPU Model
Source: SemiAnalysis InferenceX™
No reliability data available for this date range.
Shift+Scroll to zoom horizontally · Drag to pan · Double-click to reset · Hover for details