LexBench-Browser

# --split 可省略，自动使用 benchmark 的默认分片
bubench run --agent browser-use --data LexBench-Browser --mode first_n --count 5

# 评估结果（--model-id 填运行时使用的 model_id）
bubench eval --agent browser-use --data LexBench-Browser --model-id bu-2-0

{
  "id": 1,
  "query": "任务描述",
  "task_type": "T1",
  "reasoning_type": "multi_step",
  "domain": "ecommerce",
  "difficulty": "medium",
  "login_required": false,
  "login_type": "",
  "target_website": "www.example.com",
  "language": "zh",
  "website_region": "zh",
  "reference_answer": {
    "steps": ["步骤 1", "步骤 2"],
    "key_points": ["关键点 1"],
    "common_mistakes": ["常见错误 1"],
    "scoring": {
      "total": 100,
      "items": [
        {"name": "评分项", "score": 30, "description": "描述"}
      ]
    }
  }
}

{
  "task_id": "1",
  "task": "在 JD 搜索 iPhone 17，获取第一个搜索结果的价格。",
  "task_type": "T1 Info Retrieval",
  "predicted_label": 1,
  "evaluation_details": {
    "score": 85,
    "grader_response": "### 评分详情\n1. 成功搜索 iPhone 17: 10 分 / 10 分\n...",
    "screenshot_count": 1,
    "usage": {
      "total_tokens": 1690
    }
  }
}

{
  "lexmount_metrics": {
    "success_rate": 80.0,
    "success_count": 8,
    "total_tasks": 10
  },
  "score_statistics": {
    "mean": 72.5,
    "max": 95,
    "min": 45
  },
  "task_type_breakdown": {
    "T1 Info Retrieval": {
      "success_rate": 85.71
    }
  }
}