Skip to content
vs

Gemma 4 26B vs Qwen 3.8 27B: which is better at resume extraction?

Qwen 3.8 27B leads Gemma 4 26B by 20.9 points (83.8 vs 62.8 F1). Cost per 1,000 pages: $0.56 vs $9.59. Median time per resume: 29 s vs 36 s.

Gemma 4 26B wins on 19 of 300 resumes, Qwen 3.8 27B on 277, 4 tied.

62.82

Gemma 4 26B

A · Vision LLM

−20.95A − B, points of F1

83.77

Qwen 3.8 27B

B · Vision LLM

A better on 19level on 4B better on 277

Qwen 3.8 27B is ahead by 20.95 points on these 300 resumes.

  • Many entries 83A 58.0 · B 81.6−23.6
  • Long bullet lists 101A 57.4 · B 80.8−23.4
  • Split across pages 85A 60.0 · B 81.8−21.8
  • Big skills list 60A 61.9 · B 82.9−20.9
  • Custom sections 105A 58.9 · B 81.0−22.1
  • Combined headings 37A 60.9 · B 83.7−22.8
  • Promotions 88A 59.5 · B 83.2−23.7
  • Partial dates 138A 62.9 · B 83.6−20.7
  • Overlapping jobs 69A 57.5 · B 82.4−24.9
  • Accented text 13A 59.3 · B 84.9−25.7

Side by side

Gemma 4 26B vs Qwen 3.8 27B
Gemma 4 26BQwen 3.8 27B
TypeVision LLMVision LLM
MakerGoogleAlibaba
Rank16 of 189 of 18
F162.883.8
Precision69.185.4
Recall66.285.5
Cost per 1,000 pages$0.56$9.59
Median time per resume29 s36 s
Resumes won19277

Gemma 4 26B in detailQwen 3.8 27B in detail

Where each one wins

Where the two differ most.

Gemma 4 26B vs Qwen 3.8 27B by kind of resume
Kind of resume# of resumesGemma 4 26BQwen 3.8 27BGap
Scanned & rotated (source)1940.778.4−37.7
Rotated & warped pages (distractors)2143.478.7−35.3
Hidden text & prompt injections (distractors)1448.682.4−33.8
Typos kept on purpose (distractors)3751.382.9−31.7
Resume-builder templates (source)1058.686.7−28.1
Wording traps (distractors)1660.687.6−27.0
Accented text (extraction challenges)1359.384.9−25.7
Image only (reading the page)2845.170.5−25.4
Distractor layouts (source)1862.487.6−25.3
Overlapping jobs (extraction challenges)6957.582.4−24.9
Content as images (distractors)865.689.5−23.9
Promotions (extraction challenges)8859.583.2−23.7
Gemma 4 26B vs Qwen 3.8 27B by section
SectionResumesGemma 4 26BQwen 3.8 27BGap
Contact details30084.693.2−8.6
Experience30056.086.2−30.2
Education29768.087.2−19.2
Summary29035.581.7−46.2
Certifications24463.082.7−19.8
Awards11055.778.4−22.7
Skills29081.992.7−10.8
Languages17180.985.4−4.4
Custom sections22332.351.2−18.9
Interests6771.894.6−22.7
Volunteering7859.484.7−25.3
Profiles3757.272.5−15.3
Projects8355.085.5−30.5
Publications5354.577.2−22.7

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

Qwen 3.8 27B is more accurate. Gemma 4 26B costs 94% less for 20.9 fewer points.

Qwen 3.8 27B does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

Gemma 4 26B against every other model

Qwen 3.8 27B against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, Gemma 4 26B or Qwen 3.8 27B?

Qwen 3.8 27B: 83.8 F1 against 62.8.

Which is cheaper, Gemma 4 26B or Qwen 3.8 27B?

Gemma 4 26B: $0.56 per 1,000 pages against $9.59.

Where does each one do better?

Qwen 3.8 27B: scanned & rotated, rotated & warped pages and hidden text & prompt injections.