Skip to content
vs

GPT-5.6 vs Qwen 3.5 9B: which is better at resume extraction?

GPT-5.6 leads Qwen 3.5 9B by 8.7 points (84.7 vs 76.0 F1). Cost per 1,000 pages: $74 vs $1.31. Median time per resume: 38 s vs 138 s.

GPT-5.6 wins on 233 of 299 resumes, Qwen 3.5 9B on 60, 6 tied.

84.81

GPT-5.6

A · Vision LLM

+8.78A − B, points of F1

76.03

Qwen 3.5 9B

B · Vision LLM

A better on 233level on 6B better on 60

GPT-5.6 is ahead by 8.78 points on these 299 resumes.

  • Many entries 82A 84.7 · B 73.9+10.8
  • Long bullet lists 100A 85.1 · B 73.2+11.9
  • Split across pages 84A 85.1 · B 73.4+11.7
  • Big skills list 59A 85.5 · B 76.3+9.2
  • Custom sections 104A 82.3 · B 73.0+9.3
  • Combined headings 37A 84.1 · B 72.2+11.9
  • Promotions 88A 85.0 · B 74.8+10.2
  • Partial dates 138A 85.7 · B 75.6+10.1
  • Overlapping jobs 69A 83.2 · B 72.2+11.0
  • Accented text 13A 86.5 · B 83.7+2.8

Side by side

GPT-5.6 vs Qwen 3.5 9B
GPT-5.6Qwen 3.5 9B
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank6 of 1815 of 18
F184.776.0
Precision85.978.9
Recall87.280.3
Cost per 1,000 pages$74$1.31
Median time per resume38 s138 s
Resumes won23360

GPT-5.6 in detailQwen 3.5 9B in detail

Where each one wins

Where the two differ most.

GPT-5.6 vs Qwen 3.5 9B by kind of resume
Kind of resume# of resumesGPT-5.6Qwen 3.5 9BGap
Busy page (noise)1884.067.6+16.4
Long bullet lists (extraction challenges)10085.173.2+11.9
Combined headings (extraction challenges)3784.172.2+11.9
Split across pages (extraction challenges)8485.173.4+11.7
Wording traps (distractors)1689.177.7+11.4
Overlapping jobs (extraction challenges)6983.272.2+11.0
Many entries (extraction challenges)8284.773.9+10.8
Photo (reading the page)4585.574.9+10.6
Repeated header (noise)6786.876.4+10.4
References (noise)5587.977.6+10.3
Promotions (extraction challenges)8885.074.8+10.2
Partial dates (extraction challenges)13885.775.6+10.1
GPT-5.6 vs Qwen 3.5 9B by section
SectionResumesGPT-5.6Qwen 3.5 9BGap
Contact details29994.192.6+1.5
Experience29988.477.2+11.2
Education29691.980.8+11.1
Summary28983.777.9+5.8
Certifications25478.274.7+3.5
Awards9481.055.2+25.8
Skills28693.283.2+10.0
Languages16885.980.0+5.8
Custom sections21151.236.4+14.8
Interests6491.484.3+7.1
Volunteering7785.780.2+5.5
Profiles3668.551.3+17.2
Projects7989.275.5+13.7
Publications5177.876.3+1.5

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 9B costs 98% less for 8.7 fewer points.

GPT-5.6 does better on busy page, long bullet lists and combined headings.

GPT-5.6 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-5.6 or Qwen 3.5 9B?

GPT-5.6: 84.7 F1 against 76.0.

Which is cheaper, GPT-5.6 or Qwen 3.5 9B?

Qwen 3.5 9B: $1.31 per 1,000 pages against $74.

Where does each one do better?

GPT-5.6: busy page, long bullet lists and combined headings.