{
  "context": "Tests whether the agent correctly handles percentage operations in math expressions — computing percentages of values and chaining percentage and arithmetic steps with correct order of operations. Also checks that the step-by-step format and clear final answer presentation are followed.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Correct result item 1",
      "description": "Item 1: 25% of $120 is correctly calculated as $30, and discounted price stated as $90",
      "max_score": 10
    },
    {
      "name": "Correct discount item 2",
      "description": "Item 2: 15% of $85 is correctly calculated as $12.75, discounted price is $72.25",
      "max_score": 10
    },
    {
      "name": "Correct tax item 2",
      "description": "Item 2: 8% of $72.25 is correctly calculated as approximately $5.78, and final price is approximately $78.03",
      "max_score": 10
    },
    {
      "name": "Correct result item 3",
      "description": "Item 3: 30% of $340 is correctly calculated as $102, and final price is stated as $238",
      "max_score": 10
    },
    {
      "name": "Percentage step shown",
      "description": "For at least two items, the percentage conversion step is shown explicitly (e.g., converting '25%' to 0.25 or showing '25/100 × 120')",
      "max_score": 12
    },
    {
      "name": "Step-by-step work shown",
      "description": "Each item includes intermediate steps — not just a direct final answer",
      "max_score": 10
    },
    {
      "name": "Expression restated",
      "description": "Each item restates or quotes the problem being solved before the solution steps begin",
      "max_score": 8
    },
    {
      "name": "Final answer clearly stated",
      "description": "Each item ends with a clearly labeled final answer or result",
      "max_score": 10
    },
    {
      "name": "No left-to-right error",
      "description": "Item 2 does NOT skip the percentage discount step before applying tax (i.e., tax is applied to the discounted price, not the original price)",
      "max_score": 10
    },
    {
      "name": "PEMDAS steps labeled",
      "description": "At least one item uses labeled step headings corresponding to PEMDAS stages (e.g., 'Step 1', 'Step 2', or named operation labels)",
      "max_score": 10
    }
  ]
}