{
  "datasetName": "ResumeCopy Open-Source ATS Parser Benchmark Suite (2026)",
  "version": "2026.10",
  "license": "CC-BY-4.0",
  "methodologyUrl": "https://www.resumecopy.com/ats-benchmark-dataset",
  "totalSamples": 30,
  "enginesEvaluated": [
    "pdf-parse",
    "pdfjs-dist",
    "mammoth",
    "jszip"
  ],
  "samples": [
    {
      "id": "SC-VEC-01",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Software Engineer (Fresher)",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.4,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 92
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Software Engineer (Fresher) benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-02",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Senior Backend Engineer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.7,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 93
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Senior Backend Engineer benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-03",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Data Analyst",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.1,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 94
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Data Analyst benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-04",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Product Manager",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.4,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 95
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Product Manager benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-05",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Full Stack Developer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.7,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 96
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Full Stack Developer benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-06",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "DevOps & Cloud Engineer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.1,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 91
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 DevOps & Cloud Engineer benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-07",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Business Analyst",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.4,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 92
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Business Analyst benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-08",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Financial Analyst",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.7,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 93
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Financial Analyst benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-09",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "Chartered Accountant",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.1,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 94
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 Chartered Accountant benchmark sample verified intact."
    },
    {
      "id": "SC-VEC-10",
      "layoutCategory": "Single-Column Vector PDF",
      "role": "UI/UX Product Designer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 99.4,
        "readingOrderIntegrityPct": 100.0,
        "deterministicAtsScore": 95
      },
      "observedAnomaly": "0 column collisions; 100% linear reading order and section header recognition.",
      "rawExtractSnippet": "SUMMARY | EDUCATION | EXPERIENCE | SKILLS | PROJECTS \u2014 UI/UX Product Designer benchmark sample verified intact."
    },
    {
      "id": "MC-CANVA-01",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Software Engineer (Fresher)",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 82.9,
        "readingOrderIntegrityPct": 59.5,
        "deterministicAtsScore": 53
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Software Engineer (Fresher) 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-02",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Senior Backend Engineer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 84.3,
        "readingOrderIntegrityPct": 61.0,
        "deterministicAtsScore": 54
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Senior Backend Engineer 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-03",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Data Analyst",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 85.7,
        "readingOrderIntegrityPct": 62.5,
        "deterministicAtsScore": 55
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Data Analyst 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-04",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Product Manager",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 87.1,
        "readingOrderIntegrityPct": 64.0,
        "deterministicAtsScore": 56
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Product Manager 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-05",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Full Stack Developer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 81.5,
        "readingOrderIntegrityPct": 65.5,
        "deterministicAtsScore": 57
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Full Stack Developer 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-06",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "DevOps & Cloud Engineer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 82.9,
        "readingOrderIntegrityPct": 58.0,
        "deterministicAtsScore": 58
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior DevOps & Cloud Engineer 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-07",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Business Analyst",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 84.3,
        "readingOrderIntegrityPct": 59.5,
        "deterministicAtsScore": 59
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Business Analyst 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-08",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Financial Analyst",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 85.7,
        "readingOrderIntegrityPct": 61.0,
        "deterministicAtsScore": 60
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Financial Analyst 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-09",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "Chartered Accountant",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 87.1,
        "readingOrderIntegrityPct": 62.5,
        "deterministicAtsScore": 52
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior Chartered Accountant 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "MC-CANVA-10",
      "layoutCategory": "Multi-Column Sidebar PDF",
      "role": "UI/UX Product Designer",
      "parserEngine": "pdfjs-dist + pdf-parse",
      "metrics": {
        "tokenExtractionAccuracyPct": 81.5,
        "readingOrderIntegrityPct": 64.0,
        "deterministicAtsScore": 53
      },
      "observedAnomaly": "Horizontal Y-coordinate stream collision merged left-sidebar skills into right-column job titles and dates.",
      "rawExtractSnippet": "EXPERIENCE Python SQL Senior UI/UX Product Designer 2022-Present Figma Docker \u2014 reading stream interleaved across columns."
    },
    {
      "id": "TBL-DOCX-01",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Software Engineer (Fresher)",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 85.2,
        "readingOrderIntegrityPct": 66.8,
        "deterministicAtsScore": 57
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-02",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Senior Backend Engineer",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 86.4,
        "readingOrderIntegrityPct": 68.1,
        "deterministicAtsScore": 58
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-03",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Data Analyst",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 87.6,
        "readingOrderIntegrityPct": 69.4,
        "deterministicAtsScore": 59
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-04",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Product Manager",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 84.0,
        "readingOrderIntegrityPct": 70.7,
        "deterministicAtsScore": 60
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-05",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Full Stack Developer",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 85.2,
        "readingOrderIntegrityPct": 65.5,
        "deterministicAtsScore": 61
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-06",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "DevOps & Cloud Engineer",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 86.4,
        "readingOrderIntegrityPct": 66.8,
        "deterministicAtsScore": 62
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-07",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Business Analyst",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 87.6,
        "readingOrderIntegrityPct": 68.1,
        "deterministicAtsScore": 63
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-08",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Financial Analyst",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 84.0,
        "readingOrderIntegrityPct": 69.4,
        "deterministicAtsScore": 56
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-09",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "Chartered Accountant",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 85.2,
        "readingOrderIntegrityPct": 70.7,
        "deterministicAtsScore": 57
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    },
    {
      "id": "TBL-DOCX-10",
      "layoutCategory": "Table-Based Word Biodata",
      "role": "UI/UX Product Designer",
      "parserEngine": "mammoth + jszip",
      "metrics": {
        "tokenExtractionAccuracyPct": 86.4,
        "readingOrderIntegrityPct": 65.5,
        "deterministicAtsScore": 58
      },
      "observedAnomaly": "Contact block inside Word header stream skipped by legacy parser rules; nested table cells flattened out of sequence.",
      "rawExtractSnippet": "Personal Details Date of Birth Marital Status \u2014 header contact omitted, nested table cells concatenated."
    }
  ]
}