Preserves the education marks text verbatim, including the unnormalised '72 percent marks' value instead of converting it to a cleaner percentage format.
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
Research media screenshot 202026 05 05 20124544.png
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
Output — unretouched
Also checked on this input — same tool, 4 other criteria
Field coverage✓ WorkedStill covers the main resume fields on the messy input: name, email, phone, experience, education, skills, and certifications.Messy resume handling✓ WorkedHandles the noisy, inconsistent layout without crashing and still extracts the main sections.Noise in output⚠ StruggledEmits a blank Languages item when the resume has no languages section, leaving an empty placeholder instead of omitting the field.Output quality✓ WorkedProduces a usable JSON result even on the messy resume, with the important sections still readable and structured.
Provenance
- Observation
- ac039802-7f46-4988-9c6f-e70dd10c5931
- 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: "extracta-labs",
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.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.LlamaParse◐ MixedOne messy-resume education entry preserved the source phrase "72 percent marks" instead of normalizing it to a numeric percentage, while the other grades were captured as 67% and 81%.OpenResume✗ FailedWork experience mapping fails by putting a project bullet into Company and leaving Job Title empty.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