Skip to content
vs

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

Qwen 3.8 Flash leads GPT-5.5 by 0.6 points (84.1 vs 83.5 F1). Cost per 1,000 pages: $87 vs $2.98. Median time per resume: 48 s vs 122 s.

GPT-5.5 wins on 139 of 298 resumes, Qwen 3.8 Flash on 117, 42 tied.

83.67

GPT-5.5

A · Vision LLM

−0.41A − B, points of F1

84.08

Qwen 3.8 Flash

B · Vision LLM

A better on 139level on 42B better on 117

Qwen 3.8 Flash is ahead by 0.41 points on these 298 resumes.

  • Many entries 83A 83.8 · B 82.1+1.7
  • Long bullet lists 101A 84.3 · B 82.1+2.2
  • Split across pages 85A 85.0 · B 82.6+2.4
  • Big skills list 60A 85.5 · B 83.5+2.0
  • Custom sections 105A 80.8 · B 80.8−0.0
  • Combined headings 37A 83.4 · B 82.6+0.8
  • Promotions 86A 84.6 · B 83.8+0.8
  • Partial dates 138A 84.0 · B 83.3+0.7
  • Overlapping jobs 68A 82.3 · B 81.4+0.9
  • Accented text 13A 83.9 · B 86.9−3.0

Side by side

GPT-5.5 vs Qwen 3.8 Flash
GPT-5.5Qwen 3.8 Flash
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank11 of 188 of 18
F183.584.1
Precision84.985.4
Recall86.086.2
Cost per 1,000 pages$87$2.98
Median time per resume48 s122 s
Resumes won139117

GPT-5.5 in detailQwen 3.8 Flash in detail

Where each one wins

Where the two differ most.

GPT-5.5 vs Qwen 3.8 Flash by kind of resume
Kind of resume# of resumesGPT-5.5Qwen 3.8 FlashGap
Scanned & rotated (source)1761.086.3−25.3
Rotated & warped pages (distractors)1963.986.0−22.1
Hidden text & prompt injections (distractors)1369.489.0−19.7
Image only (reading the page)2656.974.7−17.8
Typos kept on purpose (distractors)3574.285.7−11.6
Content as images (distractors)892.688.3+4.3
Two-column sidebar (layout)5278.081.6−3.7
References (noise)5588.585.4+3.1
Accented text (extraction challenges)1383.986.9−3.0
Sidebar or grid (reading the page)8081.083.8−2.8
Busy page (noise)1882.579.8+2.7
Handwritten (reading the page)951.053.5−2.5
GPT-5.5 vs Qwen 3.8 Flash by section
SectionResumesGPT-5.5Qwen 3.8 FlashGap
Contact details29893.793.6+0.0
Experience29887.688.0−0.3
Education29589.090.1−1.1
Summary28982.481.3+1.1
Certifications25377.582.2−4.7
Awards9674.775.5−0.8
Skills28591.890.0+1.8
Languages16685.584.6+0.9
Custom sections20849.953.9−4.0
Interests6392.391.1+1.2
Volunteering7684.883.9+0.9
Profiles3668.573.3−4.8
Projects7986.483.7+2.7
Publications5182.581.8+0.7

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.8 Flash is more accurate. GPT-5.5 is the faster of the two.

GPT-5.5 does better on content as images, references and busy page. Qwen 3.8 Flash does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

GPT-5.5 against every other model

Qwen 3.8 Flash against every other model

Popular comparisons

Frequently asked questions (FAQs)

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

Qwen 3.8 Flash: 84.1 F1 against 83.5.

Which is cheaper, GPT-5.5 or Qwen 3.8 Flash?

Qwen 3.8 Flash: $2.98 per 1,000 pages against $87.

Where does each one do better?

GPT-5.5: content as images, references and busy page. Qwen 3.8 Flash: scanned & rotated, rotated & warped pages and hidden text & prompt injections.