Skip to content
vs

GPT-5.4 Nano vs Qwen 3.5 9B: which is better at resume extraction?

Qwen 3.5 9B leads GPT-5.4 Nano by 14.2 points (76.0 vs 61.9 F1). Cost per 1,000 pages: $2.76 vs $1.31. Median time per resume: 20 s vs 138 s.

GPT-5.4 Nano wins on 68 of 299 resumes, Qwen 3.5 9B on 229, 2 tied.

61.92

GPT-5.4 Nano

A · Vision LLM

−14.11A − B, points of F1

76.03

Qwen 3.5 9B

B · Vision LLM

A better on 68level on 2B better on 229

Qwen 3.5 9B is ahead by 14.11 points on these 299 resumes.

  • Many entries 82A 59.9 · B 73.9−14.0
  • Long bullet lists 100A 61.2 · B 73.2−12.0
  • Split across pages 84A 61.9 · B 73.4−11.5
  • Big skills list 59A 65.3 · B 76.3−11.1
  • Custom sections 104A 59.6 · B 73.0−13.4
  • Combined headings 37A 64.6 · B 72.2−7.6
  • Promotions 88A 58.7 · B 74.8−16.1
  • Partial dates 138A 62.6 · B 75.6−13.0
  • Overlapping jobs 69A 58.6 · B 72.2−13.5
  • Accented text 13A 55.9 · B 83.7−27.9

Side by side

GPT-5.4 Nano vs Qwen 3.5 9B
GPT-5.4 NanoQwen 3.5 9B
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank17 of 1815 of 18
F161.976.0
Precision70.178.9
Recall66.380.3
Cost per 1,000 pages$2.76$1.31
Median time per resume20 s138 s
Resumes won68229

GPT-5.4 Nano in detailQwen 3.5 9B in detail

Where each one wins

Where the two differ most.

GPT-5.4 Nano vs Qwen 3.5 9B by kind of resume
Kind of resume# of resumesGPT-5.4 NanoQwen 3.5 9BGap
Scanned & rotated (source)196.364.5−58.2
Rotated & warped pages (distractors)2111.766.5−54.8
Hidden text & prompt injections (distractors)1422.070.2−48.2
Image only (reading the page)2821.061.2−40.2
Typos kept on purpose (distractors)3733.572.2−38.7
Accented text (extraction challenges)1355.983.7−27.9
Content as images (distractors)861.385.9−24.6
Two-column sidebar (layout)5447.469.7−22.3
Table grid (layout)874.493.3−18.9
Expert-built (Canva / LaTeX) (source)3260.379.1−18.8
Sidebar or grid (reading the page)8254.973.5−18.6
Distractor layouts (source)1862.280.4−18.1
GPT-5.4 Nano vs Qwen 3.5 9B by section
SectionResumesGPT-5.4 NanoQwen 3.5 9BGap
Contact details29981.292.6−11.3
Experience29963.677.2−13.6
Education29662.380.8−18.5
Summary28972.077.9−6.0
Certifications24353.874.7−20.9
Awards10145.455.2−9.8
Skills29074.783.2−8.5
Languages17069.080.0−11.0
Custom sections23026.436.4−10.0
Interests6670.084.3−14.3
Volunteering8059.980.2−20.3
Profiles6522.651.3−28.8
Projects8048.875.5−26.7
Publications5130.776.3−45.6

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.5 9B is more accurate. GPT-5.4 Nano is the faster of the two.

GPT-5.4 Nano does better on handwritten. Qwen 3.5 9B does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

GPT-5.4 Nano 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-5.4 Nano or Qwen 3.5 9B?

Qwen 3.5 9B: 76.0 F1 against 61.9.

Which is cheaper, GPT-5.4 Nano or Qwen 3.5 9B?

Qwen 3.5 9B: $1.31 per 1,000 pages against $2.76.

Where does each one do better?

GPT-5.4 Nano: handwritten. Qwen 3.5 9B: scanned & rotated, rotated & warped pages and hidden text & prompt injections.