On a two-column sidebar resume, it loses reading order in work experience and duplicates 'Software Engineer — ML' into both Company and Job Title.
What was measured
Multi-column handling
Does it correctly parse two-column sidebar layouts?
decisive for this rankingtransformation
Many resumes use two-column layouts, and failing on them breaks real-world extraction quality. (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
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
Also checked on this input — same tool, 3 other criteria
Accuracy◐ MixedLeaves GPA blank and places 'Graduated: May 2019 | CGPA: 8.7/10' into Date.Accuracy◐ MixedMisclassifies the job-title headline as Summary, returning 'Software Engineer — Machine Learning' instead of a profile summary.Output quality◐ MixedText extraction is largely correct, but the overall result is only moderate because the two-column layout produces significant work-experience mapping errors.
Provenance
- Observation
- 89289907-d467-432d-9fdb-21001937df27
- 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: "openresume",
scenario: "resume-parsing"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 9 other tools
measured on Multi-column handling
Affinda✓ WorkedThe parser preserved the two-column layout well enough to extract left-column work experience and right-sidebar education, certifications, skills, and languages on first upload.Airparser✓ WorkedCorrectly parses the two-column layout, extracting left-column experience and the right-sidebar sections without losing them.CVParserPro✓ WorkedThe two-column sidebar resume was parsed without layout configuration, and content from both columns was retained well enough to extract the sidebar languages and the main work history.Extracta.ai✓ WorkedCorrectly parses a two-column sidebar layout without requiring any layout configuration.Hireability✗ FailedThe two-column sidebar layout was misread as a job-order record, so the parser returned Title, PositionTitle, and MinimumEducationLevel instead of a candidate profile.HrFlow◐ MixedIt can read a two-column/sidebar resume without crashing and pull content from both columns, but the parse is not perfectly layout-stable.LlamaParse✓ WorkedThe parser handled the two-column sidebar layout correctly and preserved content from both columns rather than dropping the right sidebar.Parseur✓ WorkedThe two-column sidebar resume was parsed correctly after template setup, so the layout did not prevent extraction of the intended fields.Skima AI✗ FailedOn the two-column sidebar layout, the parser lost the entire right-side sidebar block, so skills, certifications, and languages were not preserved in reading order.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com