HrFlow icon
developer-tools

Hrflow Review: 3 Resume Parsing Tests (2026)

HrFlow is an API-first resume parser that covers core fields well, but needs cleanup for phones, casing, and certifications.

API-basedJSON outputMulti-column parsingPhone truncation
TL;DR — our verdictUpdated August 2026 · 12 test artifacts

Solid core parser, but not production-ready without downstream cleanup

Where it wins
  • You are integrating resume parsing into a recruitment or HR product via API
  • You mainly need contact info, work history, education, and languages
  • You can normalize casing and phone formats downstream
Main limitation
  • You need phone numbers without truncation
Pricing (verified plans)
Free $0Essentials no commitmentHrTech+ Custom — billed annuallyStaffing+ Custom — billed annually
Strongest test artifacts
Output →Identity and Contact Extraction →Observation →

Feature scores on this page: 6.0/10 (1 scored feature)

Our take

HrFlow handled all three tested resumes through an API and did well on core resume structure: names, emails, work history, education, and even sidebar languages on the multi-column sample. The consistent blockers were phone truncation on 2 of 3 resumes, lowercase normalization across outputs, and unreliable certification/task extraction, so teams will need post-processing before using the data downstream.

In-Depth Review

Our detailed analysis of HrFlow — features, performance, and real-world testing.

AD
AI Demos Team
Expert Reviewer
Verified Review

Feature-by-Feature Breakdown

API-Based Resume Parsing
Works reliably as an API transport and JSON parser.
6/10
▾
Test Summary
Feature tested: API-Based Resume Parsing
Result: Partial (6/10) — Works reliably as an API transport and JSON parser.

Feature tested: API-Based Resume Parsing

Result: Partial (6/10)

Verdict: Works reliably as an API transport and JSON parser.

Expected behavior: HrFlow accepts resume PDFs through an API and returns structured JSON candidate data without template setup. The grouped cards cover a clean single-column resume, a multi-column/sidebar resume, and a messy resume, all of which were parsed without crashing.

Test case: Image → Text/code file

Input type: Image

Input used: Input artifact (Image): Input — image.png

Observed output: Output artifact (Text/code file): The clean resume parsed successfully, with name, email, phone, location, LinkedIn, job titles, companies, and education extracted; the JSON response also showed lowercased text fields and no CGPA. — hrflow output 1.txt

Input artifact: Input artifact (Image): Input — image.png

Output artifact: Output artifact (Text/code file): The clean resume parsed successfully, with name, email, phone, location, LinkedIn, job titles, companies, and education extracted; the JSON response also showed lowercased text fields and no CGPA. — hrflow output 1.txt

What changed: Image transformed into Text/code file

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input resume — image-9.png

Observed output: Output artifact (Text prompt): Observation

Input artifact: Input artifact (Image): Input resume — image-9.png

Output artifact: Output artifact (Text prompt): Observation

What changed: Image transformed into Text prompt

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input resume — image-8.png

Observed output: Output artifact (Text prompt): Observation

Input artifact: Input artifact (Image): Input resume — image-8.png

Output artifact: Output artifact (Text prompt): Observation

What changed: Image transformed into Text prompt

Why it matters / Conclusion: Reliable transport layer for API-driven parsing, but it is not a UI upload tool and the output still needs downstream cleanup for field quality.

HrFlow accepts resume PDFs through an API and returns structured JSON candidate data without template setup. The grouped cards cover a clean single-column resume, a multi-column/sidebar resume, and a messy resume, all of which were parsed without crashing.

image
Input artifact for "API-Based Resume Parsing" test: Input, image.png
↓
text
hrflow output 1.txt
Loading file...
The clean resume parsed successfully, with name, email, phone, location, LinkedIn, job titles, companies, and education extracted; the JSON response also showed lowercased text fields and no CGPA.
image
Input artifact for "API-Based Resume Parsing" test: Input resume, image-9.png
↓
OUTPUT
The Priya Sharma multi-column resume was accepted through the API and parsed without crashing into structured JSON.
image
Input artifact for "API-Based Resume Parsing" test: Input resume, image-8.png
↓
OUTPUT
The John Kumar resume was parsed successfully via API despite messy formatting, with no crash or manual mapping.
Bottom Line
Reliable transport layer for API-driven parsing, but it is not a UI upload tool and the output still needs downstream cleanup for field quality.
From our researchParse resumes into structured data using an APIearlier research
Identity and Contact Extraction
Good on basic identity fields, but phone accuracy is inconsistent.
▾
Test Summary
Feature tested: Identity and Contact Extraction
Result: Partial — Good on basic identity fields, but phone accuracy is inconsistent.

Feature tested: Identity and Contact Extraction

Result: Partial

Verdict: Good on basic identity fields, but phone accuracy is inconsistent.

Expected behavior: HrFlow extracts personal identity and contact details such as name, email, location, LinkedIn, and phone numbers from the tested resumes. The evidence shows the same contact-info capability across clean, multi-column, and messy inputs, with phone fidelity varying by resume.

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Clean resume input with a formatted phone number. — image.png

Observed output: Output artifact (Image): Rugved Nichite's phone number was returned complete. — Rugved Nichite's phone no extracted.png

Input artifact: Input artifact (Image): Clean resume input with a formatted phone number. — image.png

Output artifact: Output artifact (Image): Rugved Nichite's phone number was returned complete. — Rugved Nichite's phone no extracted.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image-9.png

Observed output: Output artifact (Image): Observation — Priya Sharma’s contact fields extracted, phone number was truncated headline lost the ML suffix..png

Input artifact: Input artifact (Image): Input resume — image-9.png

Output artifact: Output artifact (Image): Observation — Priya Sharma’s contact fields extracted, phone number was truncated headline lost the ML suffix..png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image-8.png

Observed output: Output artifact (Image): Observation — contact fields were extracted, phone retained lost the hyphen separator, and the name was lowercased..png

Input artifact: Input artifact (Image): Input resume — image-8.png

Output artifact: Output artifact (Image): Observation — contact fields were extracted, phone retained lost the hyphen separator, and the name was lowercased..png

What changed: Image transformed into Image

Why it matters / Conclusion: Solid identity extraction overall, but phone numbers are not production-safe because they failed on two of the three resumes.

HrFlow extracts personal identity and contact details such as name, email, location, LinkedIn, and phone numbers from the tested resumes. The evidence shows the same contact-info capability across clean, multi-column, and messy inputs, with phone fidelity varying by resume.

image
Input artifact for "Identity and Contact Extraction" test: Clean resume input with a formatted phone number., image.png
Clean resume input with a formatted phone number.
↓
text
Output artifact for "Identity and Contact Extraction" test: Rugved Nichite's phone number was returned complete., Rugved Nichite's phone no extracted.png
Rugved Nichite's phone number was returned complete.
image
Input artifact for "Identity and Contact Extraction" test: Input resume, image-9.png
↓
OUTPUT
Output artifact for "Identity and Contact Extraction" test: Observation, Priya Sharma’s contact fields extracted, phone number was truncated headline lost the ML suffix..png
image
Input artifact for "Identity and Contact Extraction" test: Input resume, image-8.png
↓
OUTPUT
Output artifact for "Identity and Contact Extraction" test: Observation, contact fields were extracted, phone retained lost the hyphen separator, and the name was lowercased..png
Bottom Line
Solid identity extraction overall, but phone numbers are not production-safe because they failed on two of the three resumes.
From our researchParse resumes into structured data using an API
Core Resume Section Extraction
Good core coverage for employment and education structure, with a few fidelity gaps.
▾
Test Summary
Feature tested: Core Resume Section Extraction
Result: Partial — Good core coverage for employment and education structure, with a few fidelity gaps.

Feature tested: Core Resume Section Extraction

Result: Partial

Verdict: Good core coverage for employment and education structure, with a few fidelity gaps.

Expected behavior: HrFlow extracts core resume structure including work history, job titles, employers, date ranges, education, institutions, degrees, and languages. The member cards show it also capturing responsibility/task bullets, with some truncation or pollution on harder layouts.

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Clean resume input with work experience bullets. — image.png

Observed output: Output artifact (Image): The task panel omitted the bullet about evaluating 10+ AI/ML APIs for resume parsing benchmarking and only showed the remaining tasks. — Evaluated 10+ AI ML APIs for resume parsing benchmarking.png

Input artifact: Input artifact (Image): Clean resume input with work experience bullets. — image.png

Output artifact: Output artifact (Image): The task panel omitted the bullet about evaluating 10+ AI/ML APIs for resume parsing benchmarking and only showed the remaining tasks. — Evaluated 10+ AI ML APIs for resume parsing benchmarking.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Priya Sharma resume with two certifications listed in the sidebar. — image-9.png

Observed output: Output artifact (Image): Output — certification_education_mismatch.png

Input artifact: Input artifact (Image): Priya Sharma resume with two certifications listed in the sidebar. — image-9.png

Output artifact: Output artifact (Image): Output — certification_education_mismatch.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input — image-9.png

Observed output: Output artifact (Image): Output — languages and certifications fields are extracted correctly.png

Input artifact: Input artifact (Image): Input — image-9.png

Output artifact: Output artifact (Image): Output — languages and certifications fields are extracted correctly.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image-9.png

Observed output: Output artifact (Image): The multi-column resume’s headline was truncated to 'Software Engineer — ...' even though the underlying role was 'Software Engineer — ML'; work history, education, and sidebar languages were also parsed. — image-5.png

Input artifact: Input artifact (Image): Input resume — image-9.png

Output artifact: Output artifact (Image): The multi-column resume’s headline was truncated to 'Software Engineer — ...' even though the underlying role was 'Software Engineer — ML'; work history, education, and sidebar languages were also parsed. — image-5.png

What changed: Image transformed into Image

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input resume — image-8.png

Observed output: Output artifact (Text prompt): Observation

Input artifact: Input artifact (Image): Input resume — image-8.png

Output artifact: Output artifact (Text prompt): Observation

What changed: Image transformed into Text prompt

Why it matters / Conclusion: Strong core coverage for work and education structure, with clear weaknesses around grade fields and title fidelity.

HrFlow extracts core resume structure including work history, job titles, employers, date ranges, education, institutions, degrees, and languages. The member cards show it also capturing responsibility/task bullets, with some truncation or pollution on harder layouts.

image
Input artifact for "Core Resume Section Extraction" test: Clean resume input with work experience bullets., image.png
Clean resume input with work experience bullets.
↓
file
Output artifact for "Core Resume Section Extraction" test: The task panel omitted the bullet about evaluating 10+ AI/ML APIs for resume parsing benchmarking and only showed the remaining tasks., Evaluated 10+ AI ML APIs for resume parsing benchmarking.png
The task panel omitted the bullet about evaluating 10+ AI/ML APIs for resume parsing benchmarking and only showed the remaining tasks.
image
Input artifact for "Core Resume Section Extraction" test: Priya Sharma resume with two certifications listed in the sidebar., image-9.png
Priya Sharma resume with two certifications listed in the sidebar.
↓
OUTPUT
Output artifact for "Core Resume Section Extraction" test: Output, certification_education_mismatch.png
image
Input artifact for "Core Resume Section Extraction" test: Input, image-9.png
↓
text
Output artifact for "Core Resume Section Extraction" test: Output, languages and certifications fields are extracted correctly.png
image
Input artifact for "Core Resume Section Extraction" test: Input resume, image-9.png
↓
image
Output artifact for "Core Resume Section Extraction" test: The multi-column resume’s headline was truncated to 'Software Engineer — ...' even though the underlying role was 'Software Engineer — ML'; work history, education, and sidebar languages were also parsed., image-5.png
The multi-column resume’s headline was truncated to 'Software Engineer — ...' even though the underlying role was 'Software Engineer — ML'; work history, education, and sidebar languages were also parsed.
image
Input artifact for "Core Resume Section Extraction" test: Input resume, image-8.png
↓
OUTPUT
The messy resume returned both jobs, all three education entries, and an inferred languages field, but grade and CGPA data were still absent.
Bottom Line
Strong core coverage for work and education structure, with clear weaknesses around grade fields and title fidelity.
From our researchParse resumes into structured data using an API
Skills and Certification Extraction
Weakest area: normalization, classification, and certification handling are not reliable.
▾
Test Summary
Feature tested: Skills and Certification Extraction
Result: Failed — Weakest area: normalization, classification, and certification handling are not reliable.

Feature tested: Skills and Certification Extraction

Result: Failed

Verdict: Weakest area: normalization, classification, and certification handling are not reliable.

Expected behavior: HrFlow builds a skills-oriented list from resume content, surfacing technical keywords across the tested resumes. The cards also show weaker handling around certifications and noisy outputs like lowercasing, dropped soft skills, and fragments from projects or section labels.

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image.png

Observed output: Output artifact (Image): The clean resume produced 26 skills, but the list included noise fragments such as 'lambda', 'mi', 'mi apis', and 's3', and all terms were lowercased. — image-3.png

Input artifact: Input artifact (Image): Input resume — image.png

Output artifact: Output artifact (Image): The clean resume produced 26 skills, but the list included noise fragments such as 'lambda', 'mi', 'mi apis', and 's3', and all terms were lowercased. — image-3.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image.png

Observed output: Output artifact (Image): The clean resume missed the task 'Evaluated 10+ AI/ML APIs for resume parsing benchmarking' from the extracted tasks list. — image-2.png

Input artifact: Input artifact (Image): Input resume — image.png

Output artifact: Output artifact (Image): The clean resume missed the task 'Evaluated 10+ AI/ML APIs for resume parsing benchmarking' from the extracted tasks list. — image-2.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image-9.png

Observed output: Output artifact (Image): The multi-column resume’s skills list included project fragments such as 'parse 500', 'automation tool', 'react dashboard', and split CI/CD fragments. — image-6.png

Input artifact: Input artifact (Image): Input resume — image-9.png

Output artifact: Output artifact (Image): The multi-column resume’s skills list included project fragments such as 'parse 500', 'automation tool', 'react dashboard', and split CI/CD fragments. — image-6.png

What changed: Image transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input resume — image-9.png

Observed output: Output artifact (Image): Only one Role 1 task was captured; the ML pipelines, REST APIs, and ETL migration tasks were missing. — image-7.png

Input artifact: Input artifact (Image): Input resume — image-9.png

Output artifact: Output artifact (Image): Only one Role 1 task was captured; the ML pipelines, REST APIs, and ETL migration tasks were missing. — image-7.png

What changed: Image transformed into Image

Why it matters / Conclusion: This is the weakest area: technical skills are partially captured, but normalization, classification, and certification handling are not reliable enough without manual cleanup.

HrFlow builds a skills-oriented list from resume content, surfacing technical keywords across the tested resumes. The cards also show weaker handling around certifications and noisy outputs like lowercasing, dropped soft skills, and fragments from projects or section labels.

image
Input artifact for "Skills and Certification Extraction" test: Input resume, image.png
↓
image
Output artifact for "Skills and Certification Extraction" test: The clean resume produced 26 skills, but the list included noise fragments such as 'lambda', 'mi', 'mi apis', and 's3', and all terms were lowercased., image-3.png
The clean resume produced 26 skills, but the list included noise fragments such as 'lambda', 'mi', 'mi apis', and 's3', and all terms were lowercased.
image
Input artifact for "Skills and Certification Extraction" test: Input resume, image.png
↓
image
Output artifact for "Skills and Certification Extraction" test: The clean resume missed the task 'Evaluated 10+ AI/ML APIs for resume parsing benchmarking' from the extracted tasks list., image-2.png
The clean resume missed the task 'Evaluated 10+ AI/ML APIs for resume parsing benchmarking' from the extracted tasks list.
image
Input artifact for "Skills and Certification Extraction" test: Input resume, image-9.png
↓
image
Output artifact for "Skills and Certification Extraction" test: The multi-column resume’s skills list included project fragments such as 'parse 500', 'automation tool', 'react dashboard', and split CI/CD fragments., image-6.png
The multi-column resume’s skills list included project fragments such as 'parse 500', 'automation tool', 'react dashboard', and split CI/CD fragments.
image
Input artifact for "Skills and Certification Extraction" test: Input resume, image-9.png
↓
image
Output artifact for "Skills and Certification Extraction" test: Only one Role 1 task was captured; the ML pipelines, REST APIs, and ETL migration tasks were missing., image-7.png
Only one Role 1 task was captured; the ML pipelines, REST APIs, and ETL migration tasks were missing.
Bottom Line
This is the weakest area: technical skills are partially captured, but normalization, classification, and certification handling are not reliable enough without manual cleanup.
From our researchParse resumes into structured data using an API

How it scored on the research's own criteria

The 10 evaluation dimensions from our hands-on research on HrFlow, each judged from recorded runs on 3 test inputs — the same verdicts the ranking page ranks on.

held up  partial  failed  not exercised by this input

CriterionVerdictWhat the runs showedPer inputProof
AccuracyWeak2/5The tool kept missing important details: one clean resume lost a task and a grade, the two-column resume lost title and task detail, and the messy resume lost most responsibilities. That pattern is closer to weak accuracy than acceptable precision.open proof ↗
Field coverageStrong4/5It covered the main resume sections on the clean and two-column resumes, but the messy resume lost part of the skills list, so coverage is strong rather than complete.open proof ↗
Input handlingStrong5/5This is a top score because the tool took the uploaded PDFs through the API and handled every tested resume without crashing, which is exactly what solid input handling looks like.—
Messy resume handlingMixed3/5It stayed up on the messy resume, but the output thinned out badly and one task picked up stray text, so it degraded gracefully only to a moderate degree.—
Multi-column handlingStrong5/5It successfully kept the main article and sidebar readable on the two-column resume, so the layout itself was handled well even though some content details were imperfect.open proof ↗
Noise in outputMixed3/5Wrong extras showed up on every resume, but the pollution stayed mostly in the skills or task text rather than completely breaking the result, so this lands in the middle rather than the bottom.open proof ↗
Output formatStrong5/5It consistently returned structured JSON directly from the API, so the output format is dependable and machine-friendly.—
Custom field supportWeak1/5There is no way to choose or define your own fields, so this is effectively unsupported.—
Export formatMixedNo recorded finding for this criterion — the research didn't yield an extractable observation for it, so no score can exist. Add an observation (what you did, what happened, with the artifact that shows it) to make it scorable.—
Free tier viabilityMixedWe need a run that confirms whether a free plan or trial is available. The current runs only show that an API call was needed, not whether the tool can be tested without payment.—

Verdicts come verbatim from the study's recorded observations, never re-derived at render; a criterion with no recorded run shows Not exercised — this section cannot invent a score.

Pricing & Access

TESTED
Free
$0
Up to 1,000 requests per month per API, full API documentation, community support — sufficient for testing and prototyping
Essentials
no commitment
100 free requests then billed monthly. Profile Parsing API at €0.10 per request, Text Parsing API at €0.05 per request, Tagging API at €0.01 per request. Email and chat support included. All APIs included
HrTech+
Custom — billed annually
Volume and committed-use discounts (Profile Parsing from €0.07/req), OEM and white-label options, onboarding and training, CSM and solutions engineers. For established software vendors
Staffing+
Custom — billed annually
Everything in HrTech+ plus dedicated infrastructure, custom SLA and TOS, executive roadmap briefings. For large employers and recruiting firms

Pricing checked May 2026. We re-check quarterly. HrFlow pricing is in Euros. Visit hrflow.ai for current plans and volume pricing.

✓ Use This If
●You are integrating resume parsing into a recruitment or HR product via API
●You mainly need contact info, work history, education, and languages
●You can normalize casing and phone formats downstream
●You want multi-column layout handling without manual field mapping
✕ Skip This If
●You need phone numbers without truncation
●You need certifications as a reliable structured field
●You need skills preserved with original casing and without noise fragments
●You need grade or CGPA extraction from education entries
●You need soft skills captured alongside hard skills
●You need a non-technical UI upload experience
●You need OCR or scanned-resume behavior validated in this benchmark
developer-toolsapistextFounderOther
The research shows it is API-first. It accepted PDF resumes via API, returned JSON, and did not require template or schema mapping, but it is not a pure UI upload tool.
No. On the clean resume, a certification was misclassified under Education; on the multi-column resume, certification handling was inconsistent; and on the messy resume, certifications were missing entirely.
Across the tested resumes, HrFlow returned text values such as names and skills in lowercase, so downstream normalization is needed before display or reuse.
No. The clean and multi-column resumes had truncated phone numbers, while the messy resume kept all digits but dropped the hyphen separator.
It parsed the multi-column resume without crashing and correctly extracted both roles, the degree, and the sidebar languages. The main problems were a truncated headline and noisy skills.
No. The task tested clean, multi-column, and messy text-based resumes, but it did not include a scanned or image-only resume.

Banner Preview

How the embed badge will look on your site

HrFlow featured on AI Demos

Embed HTML

Copy this code to your website source

<a target="_blank" href="https://aidemos.com/tools/hrflow?utm_source=hrflow_embed" style="width: 250px; height: 80px; border-radius:4px;" width="250" height="80"> <img src="https://aidemos-website-images.s3.amazonaws.com/featured.png" alt="HrFlow | Featured on AI Demos" style="width: 250px; height: 80px; border-radius:4px;" width="250" height="80"> </a>

Quick Integration Guide

  • 1Copy the HTML code block above.
  • 2Paste it into your site's HTML or CMS editor.
  • 3Banner appears instantly on your page.
  • 4Links back to your tool profile here.
Similar Tools

Similar Tools

Discover more AI tools like HrFlow to enhance your workflow.

🤖
Affinda
Best overall resume parsing API here for clean, multi-column, and messy PDFs with rich structured JSON.
AI Tool
🤖
Airparser
Parses clean, multi-column, and messy resumes into structured JSON, but email, title, and skill formatting still need validation.
AI Tool
🤖
Extracta.ai
Schema-first resume parsing that stays lean and predictable across clean, multi-column, and messy PDFs.
AI Tool
🤖
Skima AI
Fast PDF resume parsing with dependable core fields and experience-year calculation, but weak structured output and supplemental coverage.
AI Tool
🤖
LlamaParse
Versatile PDF parsing for Markdown and structured JSON, with strong recovery but some fidelity drift
AI Tool
🤖
Parseur
Template-driven resume parsing that returns predictable JSON after one-time setup.
AI Tool
🤖
OpenResume
Free browser resume parser that is handy for quick manual review on clean PDFs, but brittle field mapping and no JSON export make it unsuitable for API pipelines.
AI Tool
🤖
CVParserPro
Parses resume PDFs into structured candidate profiles quickly, but experience totals and education dates need manual review.
AI Tool
🤖
Hireability
Strong resume-to-JSON parsing on standard and messy single-column PDFs, but two-column layouts can break the result schema.
AI Tool
🤖
Docparser
Template-based resume parsing that works on one fixed layout, but breaks on varied resumes.
AI Tool
🤖
ResumeParser
AI Tool

Comments (0)

Please Log in to join the discussion.

Built by FutureSmart AI — the team behind AI Demos

Need a custom AI solution for this use case?

If you are looking to build a custom resume parsing, candidate data extraction, or ATS enrichment system for your business or internal workflow, email us at contact@futuresmart.ai.

Get a custom build

Found something inaccurate or missing? We try to keep our AI research accurate and useful. If you found outdated information, an issue, or have a suggestion, email us at collaborate@aidemos.com.

Back to Top