Skip to content
vs

GPT-5.4 Nano vs Qwen 3.8 Flash: which is better at resume extraction?

Qwen 3.8 Flash leads GPT-5.4 Nano by 22.2 points (84.1 vs 61.9 F1). Cost per 1,000 pages: $2.76 vs $2.98. Median time per resume: 20 s vs 122 s.

GPT-5.4 Nano wins on 33 of 298 resumes, Qwen 3.8 Flash on 264, 1 tied.

62.25

GPT-5.4 Nano

A · Vision LLM

−21.83A − B, points of F1

84.08

Qwen 3.8 Flash

B · Vision LLM

A better on 33level on 1B better on 264

Qwen 3.8 Flash is ahead by 21.83 points on these 298 resumes.

  • Many entries 83A 59.7 · B 82.1−22.4
  • Long bullet lists 101A 61.0 · B 82.1−21.0
  • Split across pages 85A 61.7 · B 82.6−20.9
  • Big skills list 60A 64.9 · B 83.5−18.6
  • Custom sections 105A 59.5 · B 80.8−21.3
  • Combined headings 37A 64.6 · B 82.6−18.0
  • Promotions 86A 60.0 · B 83.8−23.8
  • Partial dates 138A 62.6 · B 83.3−20.7
  • Overlapping jobs 68A 59.4 · B 81.4−21.9
  • Accented text 13A 55.9 · B 86.9−31.0

Side by side

GPT-5.4 Nano vs Qwen 3.8 Flash
GPT-5.4 NanoQwen 3.8 Flash
TypeVision LLMVision LLM
MakerOpenAIAlibaba
Rank17 of 188 of 18
F161.984.1
Precision70.185.4
Recall66.386.2
Cost per 1,000 pages$2.76$2.98
Median time per resume20 s122 s
Resumes won33264

GPT-5.4 Nano in detailQwen 3.8 Flash in detail

Where each one wins

Where the two differ most.

GPT-5.4 Nano vs Qwen 3.8 Flash by kind of resume
Kind of resume# of resumesGPT-5.4 NanoQwen 3.8 FlashGap
Scanned & rotated (source)176.686.3−79.7
Rotated & warped pages (distractors)1912.586.0−73.5
Hidden text & prompt injections (distractors)1323.489.0−65.6
Image only (reading the page)2622.374.7−52.4
Typos kept on purpose (distractors)3535.285.7−50.5
Two-column sidebar (layout)5249.181.6−32.5
Accented text (extraction challenges)1355.986.9−31.0
Sidebar or grid (reading the page)8056.183.8−27.7
Content as images (distractors)861.388.3−27.0
Photo (reading the page)4460.686.3−25.7
Medium (length)9060.285.3−25.1
Expert-built (Canva / LaTeX) (source)3260.384.4−24.1
GPT-5.4 Nano vs Qwen 3.8 Flash by section
SectionResumesGPT-5.4 NanoQwen 3.8 FlashGap
Contact details29881.693.6−12.1
Experience29864.188.0−23.8
Education29562.690.1−27.5
Summary28872.281.3−9.0
Certifications24353.882.2−28.4
Awards10045.875.5−29.7
Skills28975.390.0−14.7
Languages16869.784.6−14.9
Custom sections22926.653.9−27.3
Interests6571.191.1−20.1
Volunteering7960.683.9−23.3
Profiles6623.773.3−49.6
Projects8148.883.7−34.9
Publications5130.781.8−51.1

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.8 Flash is more accurate. GPT-5.4 Nano costs 7% less for 22.2 fewer points.

Qwen 3.8 Flash does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

GPT-5.4 Nano against every other model

Qwen 3.8 Flash against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, GPT-5.4 Nano or Qwen 3.8 Flash?

Qwen 3.8 Flash: 84.1 F1 against 61.9.

Which is cheaper, GPT-5.4 Nano or Qwen 3.8 Flash?

GPT-5.4 Nano: $2.76 per 1,000 pages against $2.98.

Where does each one do better?

Qwen 3.8 Flash: scanned & rotated, rotated & warped pages and hidden text & prompt injections.