Skip to content
vs

GPT-5.5 vs Qwen 3.5 9B: which is better at resume extraction?

GPT-5.5 leads Qwen 3.5 9B by 7.5 points (83.5 vs 76.0 F1). Cost per 1,000 pages: $87 vs $1.31. Median time per resume: 48 s vs 138 s.

GPT-5.5 wins on 220 of 299 resumes, Qwen 3.5 9B on 71, 8 tied.

83.52

GPT-5.5

A · Vision LLM

+7.49A − B, points of F1

76.03

Qwen 3.5 9B

B · Vision LLM

A better on 220level on 8B better on 71

GPT-5.5 is ahead by 7.49 points on these 299 resumes.

  • Many entries 82A 83.9 · B 73.9+10.0
  • Long bullet lists 100A 84.3 · B 73.2+11.2
  • Split across pages 84A 85.1 · B 73.4+11.7
  • Big skills list 59A 85.6 · B 76.3+9.3
  • Custom sections 104A 80.9 · B 73.0+7.8
  • Combined headings 37A 83.4 · B 72.2+11.2
  • Promotions 88A 84.0 · B 74.8+9.2
  • Partial dates 138A 84.0 · B 75.6+8.5
  • Overlapping jobs 69A 82.1 · B 72.2+9.9
  • Accented text 13A 83.9 · B 83.7+0.1

Side by side

GPT-5.5 vs Qwen 3.5 9B
GPT-5.5Qwen 3.5 9B
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank11 of 1815 of 18
F183.576.0
Precision84.978.9
Recall86.080.3
Cost per 1,000 pages$87$1.31
Median time per resume48 s138 s
Resumes won22071

GPT-5.5 in detailQwen 3.5 9B in detail

Where each one wins

Where the two differ most.

GPT-5.5 vs Qwen 3.5 9B by kind of resume
Kind of resume# of resumesGPT-5.5Qwen 3.5 9BGap
Busy page (noise)1882.567.6+14.9
Split across pages (extraction challenges)8485.173.4+11.7
Combined headings (extraction challenges)3783.472.2+11.2
Long bullet lists (extraction challenges)10084.373.2+11.2
References (noise)5588.577.6+10.9
Repeated header (noise)6786.776.4+10.3
Many entries (extraction challenges)8283.973.9+10.0
Overlapping jobs (extraction challenges)6982.172.2+9.9
Everyday resumes (source)21186.777.2+9.5
Big skills list (extraction challenges)5985.676.3+9.3
Long (length)6177.368.0+9.3
Two-column (layout)2388.379.1+9.2
GPT-5.5 vs Qwen 3.5 9B by section
SectionResumesGPT-5.5Qwen 3.5 9BGap
Contact details29993.592.6+0.9
Experience29987.477.2+10.2
Education29688.780.8+8.0
Summary29081.777.9+3.8
Certifications25377.374.7+2.6
Awards9775.555.2+20.3
Skills28691.583.2+8.2
Languages16885.780.0+5.7
Custom sections20949.836.4+13.4
Interests6492.484.3+8.1
Volunteering7785.080.2+4.8
Profiles3567.651.3+16.3
Projects7887.475.5+11.9
Publications5182.576.3+6.2

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

GPT-5.5 is more accurate. Qwen 3.5 9B costs 98% less for 7.5 fewer points.

GPT-5.5 does better on busy page, split across pages and combined headings. Qwen 3.5 9B does better on image only, scanned & rotated and rotated & warped pages.

GPT-5.5 against every other model

Qwen 3.5 9B against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, GPT-5.5 or Qwen 3.5 9B?

GPT-5.5: 83.5 F1 against 76.0.

Which is cheaper, GPT-5.5 or Qwen 3.5 9B?

Qwen 3.5 9B: $1.31 per 1,000 pages against $87.

Where does each one do better?

GPT-5.5: busy page, split across pages and combined headings. Qwen 3.5 9B: image only, scanned & rotated and rotated & warped pages.