The tool accepted the messy file, but it degraded badly in structure by merging bullets into a run-on responsibility line instead of preserving clean formatting.
What was measured
Messy resume handling
Does it degrade gracefully on poorly formatted input?
decisive for this rankingtransformation
Resumes are often inconsistent or poorly formatted, so graceful handling of messy input is a core capability. (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
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, 3 other criteria
Field coverage✓ WorkedEven on the messy resume, the parser still returned the core coverage set of name, email, phone, work experience, education, and skills.Noise in output✗ FailedThe messy-resume skills block was collapsed into a single concatenated string with no separators, making the field hard to reuse downstream.Output quality⚠ StruggledThe messy-resume output degraded sharply: responsibilities became a run-on string, skills collapsed into one concatenated line, and references/certifications/hobbies were missing.
Provenance
- Observation
- 862b02fa-8023-4785-8d7b-d98fd681eeed
- 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: "skima-ai",
scenario: "resume-parsing"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 9 other tools
measured on Messy resume handling
Affinda✓ WorkedThe parser handled the messy resume gracefully, still extracting the main identity, work history, education entries, skills, objective, and hobbies despite non-standard dates and raw dash-style bullets.Airparser◐ MixedParses a poorly formatted resume, but degrades into non-machine-readable skill output rather than a structured array.CVParserPro⚠ StruggledOn the messy resume, the parser collapsed the education section to 1 extracted entry and dropped the 10th- and 12th-standard records.Extracta.ai✓ WorkedHandles the noisy, inconsistent layout without crashing and still extracts the main sections.Hireability✓ WorkedOn the poorly formatted resume, the parser still recovered the main structure instead of failing outright, including contact data, experience, education, skills, and hobbies.HrFlow◐ MixedIt parses a poorly formatted resume without crashing, but degrades by dropping soft skills, omitting certifications, and losing most task bullets.LlamaParse✓ WorkedThe parser degraded gracefully on the messy resume, handling missing section headers and mixed date formats while still producing structured output.OpenResume✗ FailedOn a poorly formatted resume without bold uppercase section headers, the parser degrades badly: core sections are misassigned or empty instead of being recovered gracefully.Parseur✓ WorkedThe parser still accepted a highly inconsistent resume with missing headers and mixed date formats, and it continued parsing through the messy structure.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com