Evidence · first-party tested/Best AI Tools for Parsing Resumes via API (2026)

It again left the CGPA numeric score empty on the multi-column resume, capturing only the CGPA unit and missing the visible 8.7 value.

◐ Mixed🧾 artifact-verifiedinput + output shownTest date not recordedAffinda →
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: Multi-column sidebar resume — Priya Sharma · pdf · group: resume-parsing
Input — what we sent
parseur-input2-priya-sharma-multicolumnresume-0e443ffc95c3.pdf
Multi-column sidebar resume — Priya Sharma

A two-column sidebar resume for Priya Sharma, used to test whether parsers can preserve reading order and correctly extract content split across columns.

Why this input is hard
  • · multi-column layout handling
  • · sidebar content extraction
  • · reading-order robustness
  • · projects extraction
  • · languages and certifications extraction
Output — unretouched
Output 1
Output 1
Output 2
Output 2
Provenance
Observation
cca7d6cc-f728-4cb2-90cc-acfaf4950c07
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: "affinda",
  scenario: "resume-parsing"
})
MCP · mcp.aidemos.com/api/mcp
JSON · ai.aidemos.com/v1/observations/cca7d6cc-f728-4cb2-90cc-acfaf4950c07
Free with attribution.
Same input, same check — 7 other tools
measured on Accuracy
Airparser✓ WorkedKeeps the extracted values correct and complete on the two-column resume, including contact details, CGPA 8.7/10, project metrics, and language proficiency.CVParserPro✗ FailedThe experience calculation undercounted the candidate badly, showing 2 years even though the report says the resume reflects about 6.5 years of experience.Extracta.ai✓ WorkedCorrectly extracts the dedicated spoken-languages list as English, Hindi, and Marathi from the right-side LANGUAGES section.HrFlow◐ MixedOn the two-column resume, it truncates the job title, dropping the '— ML' suffix from 'Software Engineer — ML'.LlamaParse✓ WorkedThe multi-column resume's name, email, phone, LinkedIn URL, location, and job title headline were extracted correctly.OpenResume◐ MixedLeaves GPA blank and places 'Graduated: May 2019 | CGPA: 8.7/10' into Date.Skima AI✗ FailedThe parser truncated responsibility text mid-sentence on the multi-column resume, cutting off the quantified detail after 'cutting costs by.'
This evidence is published in
Best AI Tools for Parsing Resumes via API (2026) →
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com