InferenceX is an inference performance research platform that continually benchmarks popular open-source inference frameworks and models to track real-world performance in near real-time. It evaluates LLMs including Kimi K2.6, DeepSeekv4, and GLM5 across diverse hardware including NVIDIA GB200/B200/H100, AMD MI355X, Google TPUs, and AWS Trainium. The platform provides a live public dashboard and captures progress as inference software stacks evolve.