def grade_sample()

in browsecomp_eval.py [0:0]


    def grade_sample(self, question: str, correct_answer: str, response: str) -> str:
        grader_prompt = GRADER_TEMPLATE.format(
            question=question,
            correct_answer=correct_answer,
            response=response,
        )

        prompt_messages = [
            self.grader_model._pack_message(content=grader_prompt, role="user")
        ]
        grading_response = self.grader_model(prompt_messages)

        match = re.search(r"correct: (yes|no)", grading_response)
        return match.group(0) if match else "no"  # Default to "no" if no match