Evidence · first-party tested

The parser accepted a poorly formatted PDF without errors, but the extracted content degraded into run-on responsibilities and flattened skills, showing weak graceful degradation on messy input.

◐ Mixed🧾 artifact-verifiedSkima AI →
Input — the actual file we sent
Messy real-world resume — John Kumar
A poorly structured PDF resume for candidate John Kumar with inconsistent date formats, minimal section labeling, comma-separated skills, and mixed-in hobbies/references. It is designed to stress noisy-input robustness.
Output — unretouched
tool output
Output — unretouched
tool output
The observation

The parser accepted a poorly formatted PDF without errors, but the extracted content degraded into run-on responsibilities and flattened skills, showing weak graceful degradation on messy input.

Criterion: Messy resume handling · Scenario: Messy real-world resume — John Kumar (group: resume-parsing-benchmark)
Query this
get_evidence({
  tool: "skima-ai",
  scenario: "resume-parsing-benchmark"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, other tools
Affinda ✓ WorkedAirparser ✓ WorkedCVParserPro ◐ MixedExtracta.ai ✓ WorkedHireability ✓ WorkedHrFlow ◐ MixedLlamaparse ✓ WorkedOpenResume ✗ FailedParseur ✓ Worked
Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com