Skip to content
vs

GPT-5.4 Nano vs Qwen 3.5 35B: which is better at resume extraction?

Qwen 3.5 35B leads GPT-5.4 Nano by 16.1 points (77.9 vs 61.9 F1). Cost per 1,000 pages: $2.76 vs $3.91. Median time per resume: 20 s vs 78 s.

GPT-5.4 Nano wins on 67 of 300 resumes, Qwen 3.5 35B on 232, 1 tied.

61.86

GPT-5.4 Nano

A · Vision LLM

−16.09A − B, points of F1

77.95

Qwen 3.5 35B

B · Vision LLM

A better on 67level on 1B better on 232

Qwen 3.5 35B is ahead by 16.09 points on these 300 resumes.

  • Many entries 83A 59.7 · B 78.9−19.3
  • Long bullet lists 101A 61.0 · B 76.3−15.3
  • Split across pages 85A 61.7 · B 76.5−14.8
  • Big skills list 60A 64.9 · B 76.6−11.7
  • Custom sections 105A 59.5 · B 77.0−17.5
  • Combined headings 37A 64.6 · B 74.6−10.0
  • Promotions 88A 58.7 · B 76.7−18.0
  • Partial dates 138A 62.6 · B 78.9−16.3
  • Overlapping jobs 69A 58.6 · B 76.2−17.6
  • Accented text 13A 55.9 · B 80.4−24.6

Side by side

GPT-5.4 Nano vs Qwen 3.5 35B
GPT-5.4 NanoQwen 3.5 35B
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank17 of 1814 of 18
F161.977.9
Precision70.178.8
Recall66.383.7
Cost per 1,000 pages$2.76$3.91
Median time per resume20 s78 s
Resumes won67232

GPT-5.4 Nano in detailQwen 3.5 35B in detail

Where each one wins

Where the two differ most.

GPT-5.4 Nano vs Qwen 3.5 35B by kind of resume
Kind of resume# of resumesGPT-5.4 NanoQwen 3.5 35BGap
Scanned & rotated (source)196.375.3−69.0
Rotated & warped pages (distractors)2111.776.5−64.9
Hidden text & prompt injections (distractors)1422.079.2−57.2
Image only (reading the page)2821.069.7−48.7
Typos kept on purpose (distractors)3733.580.4−46.8
Content as images (distractors)861.390.3−29.0
Accented text (extraction challenges)1355.980.4−24.6
Two-column sidebar (layout)5447.471.5−24.1
Distractor layouts (source)1862.285.7−23.5
Expert-built (Canva / LaTeX) (source)3260.383.7−23.4
Wording traps (distractors)1662.884.8−22.0
Photo (reading the page)4559.480.0−20.6
GPT-5.4 Nano vs Qwen 3.5 35B by section
SectionResumesGPT-5.4 NanoQwen 3.5 35BGap
Contact details30081.292.1−10.9
Experience30063.779.3−15.6
Education29762.281.8−19.6
Summary29071.780.4−8.7
Certifications24453.679.1−25.5
Awards10244.961.9−16.9
Skills29174.887.8−13.0
Languages17069.079.4−10.4
Custom sections23126.340.2−13.9
Interests6670.089.7−19.7
Volunteering8059.983.1−23.3
Profiles6623.765.8−42.1
Projects8148.876.7−28.0
Publications5130.775.0−44.3

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.5 35B is more accurate. GPT-5.4 Nano costs 29% less for 16.1 fewer points.

Qwen 3.5 35B does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

GPT-5.4 Nano 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-5.4 Nano or Qwen 3.5 35B?

Qwen 3.5 35B: 77.9 F1 against 61.9.

Which is cheaper, GPT-5.4 Nano or Qwen 3.5 35B?

GPT-5.4 Nano: $2.76 per 1,000 pages against $3.91.

Where does each one do better?

Qwen 3.5 35B: scanned & rotated, rotated & warped pages and hidden text & prompt injections.