Skip to content
vs

GPT-5.5 vs Qwen 3.8 27B: which is better at resume extraction?

Qwen 3.8 27B leads GPT-5.5 by 0.3 points (83.8 vs 83.5 F1). Cost per 1,000 pages: $87 vs $9.59. Median time per resume: 48 s vs 36 s.

GPT-5.5 wins on 118 of 300 resumes, Qwen 3.8 27B on 139, 43 tied.

83.50

GPT-5.5

A · Vision LLM

−0.27A − B, points of F1

83.77

Qwen 3.8 27B

B · Vision LLM

A better on 118level on 43B better on 139

Qwen 3.8 27B is ahead by 0.27 points on these 300 resumes.

  • Many entries 83A 83.8 · B 81.6+2.2
  • Long bullet lists 101A 84.3 · B 80.8+3.5
  • Split across pages 85A 85.0 · B 81.8+3.2
  • Big skills list 60A 85.5 · B 82.9+2.6
  • Custom sections 105A 80.8 · B 81.0−0.2
  • Combined headings 37A 83.4 · B 83.7−0.3
  • Promotions 88A 84.0 · B 83.2+0.7
  • Partial dates 138A 84.0 · B 83.6+0.5
  • Overlapping jobs 69A 82.1 · B 82.4−0.3
  • Accented text 13A 83.9 · B 84.9−1.1

Side by side

GPT-5.5 vs Qwen 3.8 27B
GPT-5.5Qwen 3.8 27B
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank11 of 189 of 18
F183.583.8
Precision84.985.4
Recall86.085.5
Cost per 1,000 pages$87$9.59
Median time per resume48 s36 s
Resumes won118139

GPT-5.5 in detailQwen 3.8 27B in detail

Where each one wins

Where the two differ most.

GPT-5.5 vs Qwen 3.8 27B by kind of resume
Kind of resume# of resumesGPT-5.5Qwen 3.8 27BGap
Scanned & rotated (source)1960.778.4−17.7
Rotated & warped pages (distractors)2163.478.7−15.4
Image only (reading the page)2857.070.5−13.5
Hidden text & prompt injections (distractors)1469.182.4−13.3
Typos kept on purpose (distractors)3773.382.9−9.6
Long (length)6277.373.4+3.9
References (noise)5588.584.9+3.5
Long bullet lists (extraction challenges)10184.380.8+3.5
Split across pages (extraction challenges)8585.081.8+3.2
Content as images (distractors)892.689.5+3.1
Three-column (layout)2082.685.5−2.9
Resume-builder templates (source)1083.986.7−2.8
GPT-5.5 vs Qwen 3.8 27B by section
SectionResumesGPT-5.5Qwen 3.8 27BGap
Contact details30093.593.2+0.3
Experience30087.486.2+1.2
Education29788.787.2+1.6
Summary29181.881.7+0.1
Certifications25477.382.7−5.4
Awards9875.378.4−3.2
Skills28791.592.7−1.2
Languages16885.785.4+0.3
Custom sections21049.751.2−1.5
Interests6492.494.6−2.2
Volunteering7785.084.7+0.3
Profiles3668.572.5−4.0
Projects7986.485.5+0.9
Publications5182.577.2+5.3

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.8 27B is ahead on accuracy, cost and speed.

GPT-5.5 does better on long, references and long bullet lists. Qwen 3.8 27B does better on scanned & rotated, rotated & warped pages and image only.

GPT-5.5 against every other model

Qwen 3.8 27B against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, GPT-5.5 or Qwen 3.8 27B?

Qwen 3.8 27B: 83.8 F1 against 83.5.

Which is cheaper, GPT-5.5 or Qwen 3.8 27B?

Qwen 3.8 27B: $9.59 per 1,000 pages against $87.

Where does each one do better?

GPT-5.5: long, references and long bullet lists. Qwen 3.8 27B: scanned & rotated, rotated & warped pages and image only.