insight-bench

insight-bench copied to clipboard

Hi authors,

I'd like to confirm if the following parameters were the same as what you used in the paper:

        for model_name in ["gpt-4o"]:
            exp_list.append(
                {
                    "benchmark_type": benchmark_type,
                    "model_name": model_name,
                    "max_questions": 3,
                    "branch_depth": 4,
                }
            )

Or, alternatively, do you have the baseline results stored/published somewhere?