def make_performance_table()

in project/paperbench/experiments/judge_eval/judge_eval_perf_tables.py [0:0]

• 51 lines of code
• 8 McCabe index (conditional complexity)

def make_performance_table(model_results, random_baseline_results):
    model_to_overall = {
        model: stats["aggregate_metrics"]["f1"] for model, stats in model_results.items()
    }
    model_to_code_dev = {
        model: stats["aggregate_metrics"]["stratified"]["Code Development"]["f1"]
        for model, stats in model_results.items()
    }
    model_to_code_exec = {
        model: stats["aggregate_metrics"]["stratified"]["Code Execution"]["f1"]
        for model, stats in model_results.items()
    }
    model_to_res_analysis = {
        model: stats["aggregate_metrics"]["stratified"]["Result Analysis"]["f1"]
        for model, stats in model_results.items()
    }

    models_sorted = [
        "gpt-4o-mini-2024-07-18",
        "gpt-4o-2024-08-06",
        "o1-mini-2024-09-12_high",
        "o1-2024-12-17_high",
        "o3-mini-2025-01-31_high",
    ]

    # make table, with rows as models and columns being overall, code dev, code exec, and res analysis
    data = []
    for model in models_sorted:
        data.append(
            {
                "Model": model,
                "Overall": model_to_overall.get(model),
                "Code Development": model_to_code_dev.get(model),
                "Code Execution": model_to_code_exec.get(model),
                "Result Analysis": model_to_res_analysis.get(model),
            }
        )

    # Append random baseline row
    baseline = {
        "Model": "Random Baseline",
        "Overall": random_baseline_results.get("f1"),
        "Code Development": random_baseline_results.get("stratified", {})
        .get("Code Development", {})
        .get("f1"),
        "Code Execution": random_baseline_results.get("stratified", {})
        .get("Code Execution", {})
        .get("f1"),
        "Result Analysis": random_baseline_results.get("stratified", {})
        .get("Result Analysis", {})
        .get("f1"),
    }
    data.append(baseline)

    df = pd.DataFrame(data)
    df.to_csv("experiments/judge_eval/tables/perf_table.csv", index=False)
    print("Saved performance table to 'experiments/judge_eval/tables/perf_table.csv'")