The clean-resume output was structurally rich: skills were grouped into categorized arrays, certifications were separate objects with name/issuer/year, and work responsibilities were split into individual array items.
What was measured
Output quality
Is the parsed result clean, complete, and usable overall?
decisive for this rankingtransformation
The whole point is usable structured extraction; clean, complete, usable output is the core measure of success. (3 of 3 judges)
What was given, what came back
Test input: Clean single-column resume — Rugved Nichite · pdf · group: resume-parsing
Input — what we sent
Clean single-column resume — Rugved Nichite
A professionally structured single-column resume for Rugved Nichite, used as the baseline input for parser accuracy across standard resume fields.
Why this input is hard
- · baseline field extraction
- · contact info accuracy
- · work experience parsing
- · education and CGPA extraction
- · skills and certifications extraction
Output — unretouched
Also checked on this input — same tool, 4 other criteria
Accuracy✓ WorkedCore contact data for the clean resume — name, location, phone, email, and LinkedIn URL — was extracted correctly.Accuracy✗ FailedThe clean resume job title lost its leading "AI" prefix, so the extracted title was incomplete.Accuracy◐ MixedThe clean resume education GPA was captured, but as the string "CGPA: 8.2 / 10" instead of a clean normalized numeric value.Field coverage✓ WorkedThe clean output included the core resume fields name, email, phone, work experience, education, and skills.
Provenance
- Observation
- d74cf6a8-95be-4016-8990-a79f91b0c1dd
- Evidence run
- cbbef4db-964c-49fa-a57f-a2977822bdfc
- Study
- Parse resumes into structured data using an API
- Research task
- 86b9jm30n
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "llamaparse",
scenario: "resume-parsing"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 7 other tools
measured on Output quality
Airparser◐ MixedProduces readable, structured JSON, but the overall parse quality is reduced by a wrong email address and a truncated job title.Extracta.ai✓ WorkedReturns a clean, minimal JSON payload with the core resume sections extracted and no extra metadata noise.Hireability◐ MixedThe clean-resume output was broadly usable, but overall quality was weakened by a split name and flattened skill structure, so the result was not fully clean.HrFlow◐ MixedOverall output is usable, but the clean-resume parse still shows normalization and classification issues.OpenResume◐ MixedOn a clean single-column resume, the output is mostly usable but still partial because the Name field is blank and Phone/Location are missing.Parseur◐ MixedCGPA was embedded inside the education string rather than extracted as a dedicated field.Skima AI◐ MixedThe clean-resume output was moderately usable: the basics were correct, but certifications and GPA were missing and the responsibilities/skills sections still showed formatting artifacts.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com