10-Resume Head-to-Head

Tested against enterprise parsers. Won.

We benchmarked CVault against Affinda's resume-v4 NextGen API across 10 resumes. CVault won 74% of contested fields, lost on zero resumes. Every field scored against human-verified ground truth. No cherry-picking, no rounding.

0%win rate on contested fields
0/10structured extraction
0resumes lost
Aggregate

The scorecard

Field wins
34vs12
Win rate
74%vs26%
Resumes won
8vs0
Ties
2
Per-category

Field-by-field breakdown

How each data category performed across all 10 resumes. Scores shown as CVault–Affinda.

CategoryDistributionScore
Responsibilities10/10
10–0
Education
6–0
Phone
5–0
Certifications
5–1
Job titles
3–0
LinkedIn
2–0
Summary / Profile
1–0
Skills quantity
2–5
Email
0–1
Advantages

Where CVault wins

01

Structured responsibility extraction — 10/10

Every resume produces clean JSON arrays of individual bullet points. Affinda returns unstructured text blobs with \n separators, requiring downstream re-parsing. This is the single biggest structural advantage for ATS integration, search indexing, and AI-powered candidate matching.

02

Education extraction — 6 wins, 0 losses

CVault captured all education entries on every resume, including edge cases: General Studies at a community college, a 3-entry section on a 3-page executive resume, and 5 entries across 3 countries. Affinda missed entries on multiple resumes and misclassified certifications as education.

03

Phone extraction — 5 wins, 0 losses

Affinda dropped phone numbers on 5 of 10 resumes. CVault captured every phone number present on every resume.

04

Certification classification — 5 wins

CVault correctly separates certifications from education. Affinda folds certifications into education entries with a "Course/Certificate" level tag, conflating two distinct candidate data categories.

05

Job title accuracy — 3 wins, 0 losses

CVault preserves full job titles including geographic scope ("HEAD OF HR, INDIA"). Affinda splits geo-scoped titles incorrectly, assigns the geographic region as the employer, adds trailing commas, or drops titles entirely.

Transparency

Where they win

Honesty builds trust. These are the areas where Affinda outperformed CVault.

AffindaEmail extraction — 0 wins, 1 lossOn one resume where no email was present, CVault hallucinated one. Affinda correctly returned nothing. A real edge case to fix.
AffindaInferred skill quantity — 2 wins, 5 lossesAffinda generates more skills by inferring aggressively from job descriptions (e.g., 138 skills on a 1-page resume). CVault extracts skills closer to what is explicitly listed. More inferred skills means more noise alongside more signal — a design tradeoff, not an accuracy gap.
Shared limitations

Where both fail

BothOCR-damaged textBoth parsers produce identical errors on OCR-damaged PDFs ("SACETY COORDINATOR", "DADA/DACA SCIENTIST"). This is an upstream text extraction issue, not parser logic.
BothMissing company namesWhen resumes omit company names entirely, neither parser can invent them.
BothDOB / Nationality / Driving LicenseBoth miss these non-standard fields.
Full audit

Per-resume results

Expand any row to see the field-by-field comparison table with ground truth, CVault output, and Affinda output.

Methodology

  • 10 publicly available sample/template resumes with varied layouts, industries, and complexity. Not proprietary candidate data.
  • Ground truth established by human review of each source PDF before running either parser.
  • Both parsers run via standard pipeline with no manual review or correction.
  • "Wins" counted only on contested fields where one parser is correct and the other is incorrect or missing. Ties (both correct or both wrong) excluded from win rate.
  • Skill quantity comparisons favor the parser with more skills — acknowledged as a design tradeoff, not a pure accuracy metric.
  • Resume 10 (Accountant) audited separately with full per-field comparison; results consistent with the 9-resume batch. Including resume 10: CVault 38–13 Affinda, 75% win rate.
  • Tested against Affinda specifically. Not a claim of superiority over all resume parsers.

Benchmark date: March 19, 2026 · CVault: CVault API v1 · Affinda: resume-v4 (NextGen), via API

Don't take our word for it

Upload a resume and see CVault's parse result. No credit card, no sales call.

Try CVault freeRead the API docs