PyPI Stats

Search

All packages
Top packages

Track packages

llm-benchmark-toolkit


PyPI page
Home page
Author: None
Summary: Benchmark LLMs with 10 benchmarks & 132K+ questions. 8 providers: OpenAI, Anthropic, Groq, Together, Fireworks, DeepSeek, Ollama, HuggingFace. Unified CLI + Web dashboard.
Latest version: 2.4.2
Required dependencies: anthropic | click | datasets | fastapi | huggingface-hub | matplotlib | numpy | ollama | openai | pandas | plotly | psutil | pydantic | pydantic-settings | scikit-learn | scipy | seaborn | sse-starlette | tqdm | uvicorn
Optional dependencies: anthropic | black | fastapi | flake8 | huggingface-hub | ipykernel | ipywidgets | jupyter | mypy | openai | pytest | pytest-cov | pytest-mock | ruff | sse-starlette | types-requests | uvicorn

Downloads last day: 0
Downloads last week: 217
Downloads last month: 260