bench-my-llm is an open-source command-line tool for benchmarking OpenAI-compatible language model APIs. It measures time to first token, tokens per second, latency, cost, and output quality for developers evaluating LLM services.
bench-my-llm sits in PulseGate's LLM evaluation & benchmarks category. It focuses on comparing LLM API performance, cost, latency, and output quality without building custom benchmarking scripts. bench-my-llm is an open-source project aimed at developers and ML engineers. bench-my-llm is open source under the MIT license. bench-my-llm is available on the command line and API.
It is developed by Manas Vardhan, and it first shipped in 2026. The project is developed in the open on GitHub with 58 stars and 11 commits in the last 90 days. Among its 8 catalogued features are TTFT measurement, TPS measurement, and latency tracking. It exposes integrations via a public API.
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