Skip to content
vs

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

Qwen 3.8 27B leads Reducto Extract by 2.1 points (83.8 vs 81.7 F1). Cost per 1,000 pages: $9.59 vs $20. Median time per resume: 36 s vs 16 s.

Qwen 3.8 27B wins on 161 of 300 resumes, Reducto Extract on 116, 23 tied.

83.77

Qwen 3.8 27B

A · Vision LLM

+2.07A − B, points of F1

81.70

Reducto Extract

B · Document API

A better on 161level on 23B better on 116

Qwen 3.8 27B is ahead by 2.07 points on these 300 resumes.

  • Many entries 83A 81.6 · B 79.5+2.2
  • Long bullet lists 101A 80.8 · B 80.2+0.6
  • Split across pages 85A 81.8 · B 79.7+2.1
  • Big skills list 60A 82.9 · B 83.2−0.3
  • Custom sections 105A 81.0 · B 78.2+2.7
  • Combined headings 37A 83.7 · B 80.2+3.5
  • Promotions 88A 83.2 · B 82.8+0.4
  • Partial dates 138A 83.6 · B 80.0+3.6
  • Overlapping jobs 69A 82.4 · B 80.4+2.0
  • Accented text 13A 84.9 · B 87.8−2.8

Side by side

Qwen 3.8 27B vs Reducto Extract
Qwen 3.8 27BReducto Extract
TypeVision LLMDocument API
MakerAlibabaReducto
Rank9 of 1812 of 18
F183.881.7
Precision85.483.7
Recall85.584.0
Cost per 1,000 pages$9.59$20
Median time per resume36 s16 s
Resumes won161116

Qwen 3.8 27B in detailReducto Extract in detail

Where each one wins

Where the two differ most.

Qwen 3.8 27B vs Reducto Extract by kind of resume
Kind of resume# of resumesQwen 3.8 27BReducto ExtractGap
Handwritten (reading the page)951.639.4+12.2
Scanned & rotated (source)1978.489.9−11.5
Rotated & warped pages (distractors)2178.789.2−10.5
Wording traps (distractors)1687.681.4+6.2
Three-column (layout)2085.579.9+5.6
Distractor layouts (source)1887.682.3+5.4
Table grid (layout)895.790.8+5.0
Resume-builder templates (source)1086.781.8+4.9
Busy page (noise)1880.475.4+4.9
Hidden text & prompt injections (distractors)1482.487.2−4.8
Two-column (layout)2387.983.2+4.7
Content as images (distractors)889.584.9+4.6
Qwen 3.8 27B vs Reducto Extract by section
SectionResumesQwen 3.8 27BReducto ExtractGap
Contact details30093.293.4−0.3
Experience30086.284.0+2.2
Education29787.282.3+4.8
Summary29081.781.7+0.0
Certifications24482.781.3+1.4
Awards9778.473.5+5.0
Skills28492.793.0−0.3
Languages16885.484.3+1.0
Custom sections21651.244.4+6.8
Interests6394.692.8+1.8
Volunteering7984.782.7+2.0
Profiles3472.558.1+14.5
Projects7885.584.6+0.9
Publications5177.276.0+1.2

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.8 27B is more accurate. Reducto Extract is the faster of the two.

Qwen 3.8 27B does better on handwritten, wording traps and three-column. Reducto Extract does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

Qwen 3.8 27B against every other model

Reducto Extract against every other model

Popular comparisons

Frequently asked questions (FAQs)

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

Qwen 3.8 27B: 83.8 F1 against 81.7.

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

Qwen 3.8 27B: $9.59 per 1,000 pages against $20.

Where does each one do better?

Qwen 3.8 27B: handwritten, wording traps and three-column. Reducto Extract: scanned & rotated, rotated & warped pages and hidden text & prompt injections.