Produces readable, structured JSON, but the overall parse quality is reduced by a wrong email address and a truncated job title.
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◐ MixedMisreads the email local-part on a clean resume, returning "rugged.nichite@email.com" instead of "rugved.nichite@email.com".Accuracy◐ MixedSilently truncates a compound job title, returning "AI Research Analyst" and dropping "& Software Developer".Field coverage✓ WorkedCovers the baseline resume fields end to end: name, email, phone, work experience, education, and skills.Input handling✓ WorkedAccepts a PDF resume directly and parses it on first upload without manual configuration.
Provenance
- Observation
- 92e8644f-bb57-441f-9a69-f288f51acec1
- 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: "airparser",
scenario: "resume-parsing"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 7 other tools
measured on Output quality
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.LlamaParse✓ WorkedThe 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.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