Metadata-Version: 2.5
Name: pergamon-bench
Version: 0.8.6
Summary: Pergamon Bench: the OpenCode agent wrapper for Harbor, with the grader and job configurations
Project-URL: Dataset, https://github.com/pergamon-ai/pergamon-bench
Project-URL: Source, https://github.com/pergamon-ai/pergamon-bench-eval
Author: Pergamon
License-Expression: Apache-2.0
License-File: LICENSE
License-File: NOTICE
Keywords: benchmark,evaluation,harbor,law,llm
Requires-Python: >=3.12
Requires-Dist: harbor-rewardkit<0.3,>=0.2.1
Requires-Dist: harbor<0.24,>=0.23.0
Requires-Dist: httpx>=0.27
Requires-Dist: litellm>=1.92.0
Requires-Dist: pydantic>=2.12
Requires-Dist: pyyaml>=6.0
Requires-Dist: tenacity>=9.1
Provides-Extra: dev
Requires-Dist: kubernetes>=32.0.0; extra == 'dev'
Requires-Dist: pbench-search; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.24; extra == 'dev'
Requires-Dist: pytest>=8; extra == 'dev'
Requires-Dist: ruff>=0.6; extra == 'dev'
Provides-Extra: k8s
Requires-Dist: kubernetes>=32.0.0; extra == 'k8s'
Provides-Extra: redis
Requires-Dist: redis>=5.0; extra == 'redis'
Description-Content-Type: text/markdown

# pergamon-bench

The code behind Pergamon Bench, a benchmark of legal reasoning and research tasks on
continental-European law, run with [Harbor](https://github.com/laude-institute/harbor):
the agent wrapper Harbor loads, the exercise-to-task converter and the grader.

Documentation and the dataset will be published with the first public release.
