On the messy resume, the name, email, phone, location, and objective statement were extracted correctly.
What was measured
Accuracy
Are extracted values correct and complete?
decisive for this rankingtransformation
Correct and complete values are the essence of resume parsing, so this directly determines whether the tool succeeds. (3 of 3 judges)
What was given, what came back
Test input: Messy real-world resume — John Kumar · pdf · group: resume-parsing
Input — what we sent
Messy real-world resume — John Kumar
A poorly formatted, inconsistent real-world resume for John Kumar, used to test robustness against noisy structure, inconsistent dates, and mixed-content sections.
Why this input is hard
- · messy formatting robustness
- · section detection fallback
- · inconsistent date parsing
- · soft-skills extraction
- · noise and hallucination control
Also checked on this input — same tool, 3 other criteria
Field coverage✓ WorkedThe messy-resume output included the core fields and additional sections: name, contact information, objective, work experience, education, skills, certifications, hobbies, and references.Messy resume handling✓ WorkedThe parser degraded gracefully on the messy resume, handling missing section headers and mixed date formats while still producing structured output.Output quality✓ WorkedThe messy-resume output was the richest and cleanest among the tested tools, with all 3 education entries, all 14 skills, both certifications, hobbies, and a boolean references field.
Provenance
- Observation
- c90b4e68-d0af-47f9-a85c-43c3ec8a9fac
- 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 — 8 other tools
measured on Accuracy
Affinda✗ FailedIts total experience calculation overstates tenure: it returned 7.3 years even though the resume explicitly says 3 years of experience.Airparser◐ MixedLeaves one education marks value as raw text ("72 percent marks") instead of normalizing it to the percentage form used by the other entries.CVParserPro✗ FailedThe education end date was wrong: a completed program was rendered as ending in Present.Extracta.ai◐ MixedReturns both certification names in lowercase exactly as written, with no capitalization normalisation applied.Hireability✗ FailedThe second employer name was merged with the role title, returning 'Junior Developer XYZ InfoTech' instead of just 'XYZ InfoTech'.HrFlow◐ MixedOn the messy resume, it keeps the main contact/work/education structure but misses the soft-skill section and certification entries.OpenResume✗ FailedEducation parsing collapses: School and Degree are empty, GPA is misread as 12, and the full education line is pushed into Date.Parseur✗ FailedThe education CGPA value was wrong: the tool returned 67, which the report says is the percentage score rather than the actual CGPA.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com