自定义 Benchmark

benchmarks/
└── <YourBenchmark>/
    ├── README.md           # Benchmark 说明文档
    ├── data/
    │   └── tasks.json      # 任务数据
    ├── data_info.json      # 数据分割信息
    └── evaluator.py        # 评估脚本（可选）

[
  {
    "task_id": "your_task_001",
    "task": "任务描述，Agent 将看到这个描述",
    "website": "example.com",
    "category": "信息获取",
    "expected_result": "期望的结果描述",
    "requires_login": false,
    "difficulty": "easy"
  },
  {
    "task_id": "your_task_002",
    "task": "另一个任务描述",
    "website": "example.org",
    "category": "表单填写",
    "expected_result": "表单提交成功",
    "requires_login": true,
    "difficulty": "medium"
  }
]

{
  "name": "YourBenchmark",
  "description": "你的 Benchmark 描述",
  "default_split": "All",
  "split": {
    "All": "tasks.json",
    "Easy": "tasks_easy.json",
    "Medium": "tasks_medium.json",
    "Hard": "tasks_hard.json"
  }
}

from browseruse_bench.eval.base_evaluator import BaseEvaluator

class YourBenchmarkEvaluator(BaseEvaluator):
    """自定义评估器"""
    
    def evaluate_task(self, task_id: str, result: dict) -> dict:
        """
        评估单个任务
        
        Args:
            task_id: 任务 ID
            result: Agent 返回的结果
            
        Returns:
            评估结果字典，包含 predicted_label 和 score
        """
        # 你的评估逻辑
        score = self._calculate_score(result)
        
        return {
            "predicted_label": 1 if score >= 60 else 0,
            "score": score,
            "evaluation_details": {
                "grader_response": "评估详情..."
            }
        }

BENCHMARKS = {
    "LexBench-Browser": ...,
    "Online-Mind2Web": ...,
    "BrowseComp": ...,
    "YourBenchmark": {
        "data_dir": "benchmarks/YourBenchmark",
        "evaluator": "browseruse_bench.eval.your_evaluator:YourBenchmarkEvaluator"
    }
}

# 测试运行
bubench run \
  --agent browser-use \
  --data YourBenchmark \
  --mode first_n --count 3

# 测试评估
bubench eval \
  --agent browser-use \
  --data YourBenchmark \
  --model-id bu-2-0