Skip to content
vs

GPT-5.6 vs Qwen 3.5 35B: which is better at resume extraction?

GPT-5.6 leads Qwen 3.5 35B by 6.8 points (84.7 vs 77.9 F1). Cost per 1,000 pages: $74 vs $3.91. Median time per resume: 38 s vs 78 s.

GPT-5.6 wins on 212 of 300 resumes, Qwen 3.5 35B on 81, 7 tied.

84.75

GPT-5.6

A · Vision LLM

+6.80A − B, points of F1

77.95

Qwen 3.5 35B

B · Vision LLM

A better on 212level on 7B better on 81

GPT-5.6 is ahead by 6.80 points on these 300 resumes.

  • Many entries 83A 84.5 · B 78.9+5.5
  • Long bullet lists 101A 84.9 · B 76.3+8.6
  • Split across pages 85A 84.9 · B 76.5+8.4
  • Big skills list 60A 85.2 · B 76.6+8.5
  • Custom sections 105A 82.2 · B 77.0+5.1
  • Combined headings 37A 84.1 · B 74.6+9.5
  • Promotions 88A 85.0 · B 76.7+8.3
  • Partial dates 138A 85.7 · B 78.9+6.8
  • Overlapping jobs 69A 83.2 · B 76.2+7.0
  • Accented text 13A 86.5 · B 80.4+6.1

Side by side

GPT-5.6 vs Qwen 3.5 35B
GPT-5.6Qwen 3.5 35B
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank6 of 1814 of 18
F184.777.9
Precision85.978.8
Recall87.283.7
Cost per 1,000 pages$74$3.91
Median time per resume38 s78 s
Resumes won21281

GPT-5.6 in detailQwen 3.5 35B in detail

Where each one wins

Where the two differ most.

GPT-5.6 vs Qwen 3.5 35B by kind of resume
Kind of resume# of resumesGPT-5.6Qwen 3.5 35BGap
Busy page (noise)1884.071.8+12.2
Two-column (layout)2389.077.4+11.6
Three-column (layout)2085.675.6+10.0
Combined headings (extraction challenges)3784.174.6+9.5
Everyday resumes (source)21286.877.7+9.1
Long bullet lists (extraction challenges)10184.976.3+8.6
Big skills list (extraction challenges)6085.276.6+8.5
Split across pages (extraction challenges)8584.976.5+8.4
Promotions (extraction challenges)8885.076.7+8.3
Repeated header (noise)6786.878.6+8.3
Short (length)14887.279.8+7.4
Overlapping jobs (extraction challenges)6983.276.2+7.0
GPT-5.6 vs Qwen 3.5 35B by section
SectionResumesGPT-5.6Qwen 3.5 35BGap
Contact details30094.192.1+2.0
Experience30088.479.3+9.1
Education29791.981.8+10.1
Summary29083.480.4+3.0
Certifications25577.979.1−1.2
Awards9581.261.9+19.3
Skills28793.287.8+5.4
Languages16885.979.4+6.5
Custom sections21251.240.2+11.0
Interests6491.489.7+1.6
Volunteering7785.783.1+2.5
Profiles3769.465.8+3.6
Projects8088.276.7+11.4
Publications5177.875.0+2.8

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

GPT-5.6 is more accurate. Qwen 3.5 35B costs 95% less for 6.8 fewer points.

GPT-5.6 does better on busy page, two-column and three-column. Qwen 3.5 35B does better on image only, scanned & rotated and rotated & warped pages.

GPT-5.6 against every other model

Qwen 3.5 35B against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, GPT-5.6 or Qwen 3.5 35B?

GPT-5.6: 84.7 F1 against 77.9.

Which is cheaper, GPT-5.6 or Qwen 3.5 35B?

Qwen 3.5 35B: $3.91 per 1,000 pages against $74.

Where does each one do better?

GPT-5.6: busy page, two-column and three-column. Qwen 3.5 35B: image only, scanned & rotated and rotated & warped pages.