Skip to content
vs

Qwen 3.8 27B vs Reducto Deep Extract: which is better at resume extraction?

Reducto Deep Extract leads Qwen 3.8 27B by 1.8 points (85.6 vs 83.8 F1). Cost per 1,000 pages: $9.59 vs $40. Median time per resume: 36 s vs 65 s.

Qwen 3.8 27B wins on 102 of 300 resumes, Reducto Deep Extract on 152, 46 tied.

83.77

Qwen 3.8 27B

A · Vision LLM

−1.78A − B, points of F1

85.55

Reducto Deep Extract

B · Document API

A better on 102level on 46B better on 152

Reducto Deep Extract is ahead by 1.78 points on these 300 resumes.

  • Many entries 83A 81.6 · B 84.3−2.7
  • Long bullet lists 101A 80.8 · B 84.5−3.7
  • Split across pages 85A 81.8 · B 84.1−2.3
  • Big skills list 60A 82.9 · B 85.8−2.9
  • Custom sections 105A 81.0 · B 82.6−1.6
  • Combined headings 37A 83.7 · B 82.7+1.0
  • Promotions 88A 83.2 · B 86.0−2.7
  • Partial dates 138A 83.6 · B 85.2−1.6
  • Overlapping jobs 69A 82.4 · B 85.9−3.5
  • Accented text 13A 84.9 · B 85.5−0.5

Side by side

Qwen 3.8 27B vs Reducto Deep Extract
Qwen 3.8 27BReducto Deep Extract
TypeVision LLMDocument API
MakerAlibabaReducto
Rank9 of 182 of 18
F183.885.6
Precision85.487.5
Recall85.587.3
Cost per 1,000 pages$9.59$40
Median time per resume36 s65 s
Resumes won102152

Qwen 3.8 27B in detailReducto Deep Extract in detail

Where each one wins

Where the two differ most.

Qwen 3.8 27B vs Reducto Deep Extract by kind of resume
Kind of resume# of resumesQwen 3.8 27BReducto Deep ExtractGap
Scanned & rotated (source)1978.490.1−11.7
Rotated & warped pages (distractors)2178.789.3−10.5
Resume-builder templates (source)1086.777.6+9.1
Hidden text & prompt injections (distractors)1482.490.1−7.7
Image only (reading the page)2870.576.4−5.9
Two-column sidebar (layout)5478.483.8−5.4
References (noise)5584.990.2−5.3
Typos kept on purpose (distractors)3782.987.9−5.0
Long (length)6273.477.5−4.1
Long bullet lists (extraction challenges)10180.884.5−3.7
Overlapping jobs (extraction challenges)6982.485.9−3.5
Sidebar or grid (reading the page)8281.885.2−3.5
Qwen 3.8 27B vs Reducto Deep Extract by section
SectionResumesQwen 3.8 27BReducto Deep ExtractGap
Contact details30093.294.2−1.1
Experience30086.290.6−4.4
Education29787.292.0−4.8
Summary29081.785.2−3.4
Certifications24482.781.4+1.3
Awards9778.479.4−1.0
Skills28492.793.9−1.2
Languages16885.481.8+3.6
Custom sections21651.251.3−0.1
Interests6394.693.8+0.8
Volunteering7984.789.5−4.9
Profiles3472.569.6+2.9
Projects7885.588.1−2.6
Publications5177.279.3−2.1

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Reducto Deep Extract is more accurate. Qwen 3.8 27B costs 76% less for 1.8 fewer points.

Qwen 3.8 27B does better on resume-builder templates, wording traps and table grid. Reducto Deep Extract does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

Qwen 3.8 27B against every other model

Reducto Deep Extract against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, Qwen 3.8 27B or Reducto Deep Extract?

Reducto Deep Extract: 85.6 F1 against 83.8.

Which is cheaper, Qwen 3.8 27B or Reducto Deep Extract?

Qwen 3.8 27B: $9.59 per 1,000 pages against $40.

Where does each one do better?

Qwen 3.8 27B: resume-builder templates, wording traps and table grid. Reducto Deep Extract: scanned & rotated, rotated & warped pages and hidden text & prompt injections.