llm-benchmark-runner is an open-source CLI tool that allows developers and researchers to benchmark the inference latency and throughput of large language model APIs. It supports OpenAI-compatible endpoints and provides detailed performance metrics for model evaluation.
In the AI space, llm-benchmark-runner takes a focused approach. It focuses on measuring and comparing the latency and performance of large language model inference APIs for developers and researchers. llm-benchmark-runner is an open-source project aimed at AI researchers and developers. The project is open source (MIT). llm-benchmark-runner is available on the command line.
Behind llm-benchmark-runner is kuhung, and it first shipped in 2026. Development happens publicly on GitHub with 29 commits in the last 90 days. Key capabilities include LLM benchmarking, latency measurement, and API compatibility.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do