├── .gitignore ├── README.md ├── USACOBench ├── __init__.py ├── agents │ ├── __init__.py │ ├── baselines.py │ └── prompts.py ├── data_utils.py ├── display_utils.py ├── evaluation │ ├── __init__.py │ ├── evaluate.py │ ├── judges │ │ ├── __init__.py │ │ ├── codeforces_judge.py │ │ ├── codeforces_utils.py │ │ ├── judge.py │ │ ├── usaco_batch_judge.py │ │ ├── usaco_judge.py │ │ └── usaco_utils.py │ ├── metrics.py │ ├── result_type.py │ └── utils.py ├── models │ ├── __init__.py │ ├── gpt.py │ ├── models.py │ └── utils.py ├── prompts.py ├── retrievers │ ├── __init__.py │ ├── retrievers.py │ └── utils.py ├── tools │ ├── __init__.py │ ├── pdb_tool.py │ ├── sandbox.py │ ├── tools.py │ └── utils.py └── utils.py ├── evaluate.py ├── evaluate_solution_sets.py ├── models.py ├── requirements.txt ├── run_usaco.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/README.md -------------------------------------------------------------------------------- /USACOBench/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /USACOBench/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/agents/__init__.py -------------------------------------------------------------------------------- /USACOBench/agents/baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/agents/baselines.py -------------------------------------------------------------------------------- /USACOBench/agents/prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/agents/prompts.py -------------------------------------------------------------------------------- /USACOBench/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/data_utils.py -------------------------------------------------------------------------------- /USACOBench/display_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/display_utils.py -------------------------------------------------------------------------------- /USACOBench/evaluation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/__init__.py -------------------------------------------------------------------------------- /USACOBench/evaluation/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/evaluate.py -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/codeforces_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/judges/codeforces_judge.py -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/codeforces_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/judges/codeforces_utils.py -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/judges/judge.py -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/usaco_batch_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/judges/usaco_batch_judge.py -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/usaco_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/judges/usaco_judge.py -------------------------------------------------------------------------------- /USACOBench/evaluation/judges/usaco_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/judges/usaco_utils.py -------------------------------------------------------------------------------- /USACOBench/evaluation/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/metrics.py -------------------------------------------------------------------------------- /USACOBench/evaluation/result_type.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/result_type.py -------------------------------------------------------------------------------- /USACOBench/evaluation/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/evaluation/utils.py -------------------------------------------------------------------------------- /USACOBench/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/models/__init__.py -------------------------------------------------------------------------------- /USACOBench/models/gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/models/gpt.py -------------------------------------------------------------------------------- /USACOBench/models/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/models/models.py -------------------------------------------------------------------------------- /USACOBench/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/models/utils.py -------------------------------------------------------------------------------- /USACOBench/prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/prompts.py -------------------------------------------------------------------------------- /USACOBench/retrievers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/retrievers/__init__.py -------------------------------------------------------------------------------- /USACOBench/retrievers/retrievers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/retrievers/retrievers.py -------------------------------------------------------------------------------- /USACOBench/retrievers/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/retrievers/utils.py -------------------------------------------------------------------------------- /USACOBench/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/tools/__init__.py -------------------------------------------------------------------------------- /USACOBench/tools/pdb_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/tools/pdb_tool.py -------------------------------------------------------------------------------- /USACOBench/tools/sandbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/tools/sandbox.py -------------------------------------------------------------------------------- /USACOBench/tools/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/tools/tools.py -------------------------------------------------------------------------------- /USACOBench/tools/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/tools/utils.py -------------------------------------------------------------------------------- /USACOBench/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/USACOBench/utils.py -------------------------------------------------------------------------------- /evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/evaluate.py -------------------------------------------------------------------------------- /evaluate_solution_sets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/evaluate_solution_sets.py -------------------------------------------------------------------------------- /models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/models.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/requirements.txt -------------------------------------------------------------------------------- /run_usaco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/run_usaco.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/princeton-nlp/USACO/HEAD/utils.py --------------------------------------------------------------------------------