PyPI page
Home page
Author:
Xavier Puspus
Summary:
Benchmark harness measuring AI coding tool+workflow performance, not just model capability. 100 tasks, sigmoid scoring, 12 capability dimensions, gap analysis.
Latest version:
1.4.0
Required dependencies:
click
|
jinja2
|
jsonschema
|
pyyaml
|
rich
|
tabulate
Optional dependencies:
build
|
numpy
|
pytest
|
pytest-asyncio
|
ruff
|
scipy
|
twine
Downloads last day:
8
Downloads last week:
133
Downloads last month:
344