Skip to content
vs

LlamaParse Extract Agentic vs Qwen 3.8 27B: which is better at resume extraction?

LlamaParse Extract Agentic leads Qwen 3.8 27B by 1.8 points (85.5 vs 83.8 F1). Cost per 1,000 pages: $23 vs $9.59. Median time per resume: 55 s vs 36 s.

LlamaParse Extract Agentic wins on 145 of 300 resumes, Qwen 3.8 27B on 103, 52 tied.

85.55

LlamaParse Extract Agentic

A · Document API

+1.78A − B, points of F1

83.77

Qwen 3.8 27B

B · Vision LLM

A better on 145level on 52B better on 103

LlamaParse Extract Agentic is ahead by 1.78 points on these 300 resumes.

  • Many entries 83A 83.0 · B 81.6+1.4
  • Long bullet lists 101A 83.1 · B 80.8+2.3
  • Split across pages 85A 83.8 · B 81.8+2.0
  • Big skills list 60A 83.7 · B 82.9+0.9
  • Custom sections 105A 82.5 · B 81.0+1.5
  • Combined headings 37A 83.2 · B 83.7−0.5
  • Promotions 88A 85.5 · B 83.2+2.3
  • Partial dates 138A 85.6 · B 83.6+2.0
  • Overlapping jobs 69A 83.5 · B 82.4+1.1
  • Accented text 13A 91.1 · B 84.9+6.2

Side by side

LlamaParse Extract Agentic vs Qwen 3.8 27B
LlamaParse Extract AgenticQwen 3.8 27B
TypeDocument APIVision LLM
MakerLlamaIndexAlibaba
Rank3 of 189 of 18
F185.583.8
Precision86.885.4
Recall87.385.5
Cost per 1,000 pages$23$9.59
Median time per resume55 s36 s
Resumes won145103

LlamaParse Extract Agentic in detailQwen 3.8 27B in detail

Where each one wins

Where the two differ most.

LlamaParse Extract Agentic vs Qwen 3.8 27B by kind of resume
Kind of resume# of resumesLlamaParse Extract AgenticQwen 3.8 27BGap
Scanned & rotated (source)1991.678.4+13.2
Rotated & warped pages (distractors)2190.978.7+12.2
Handwritten (reading the page)963.551.6+11.9
Image only (reading the page)2881.570.5+11.0
Hidden text & prompt injections (distractors)1491.682.4+9.2
Typos kept on purpose (distractors)3790.082.9+7.1
Accented text (extraction challenges)1391.184.9+6.2
Two-column sidebar (layout)5484.078.4+5.7
Long (length)6278.073.4+4.6
Sidebar or grid (reading the page)8285.581.8+3.7
Resume-builder templates (source)1083.286.7−3.5
Busy page (noise)1883.580.4+3.2
LlamaParse Extract Agentic vs Qwen 3.8 27B by section
SectionResumesLlamaParse Extract AgenticQwen 3.8 27BGap
Contact details30094.593.2+1.4
Experience30089.686.2+3.4
Education29791.387.2+4.1
Summary29084.581.7+2.8
Certifications25280.982.7−1.8
Awards9380.378.4+1.9
Skills28695.192.7+2.4
Languages16784.285.4−1.2
Custom sections20852.151.2+0.9
Interests6493.094.6−1.6
Volunteering7787.784.7+3.0
Profiles3567.672.5−4.9
Projects7886.285.5+0.7
Publications5180.577.2+3.3

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

LlamaParse Extract Agentic is more accurate. Qwen 3.8 27B costs 58% less for 1.8 fewer points.

LlamaParse Extract Agentic does better on scanned & rotated, rotated & warped pages and handwritten. Qwen 3.8 27B does better on resume-builder templates and medium.

LlamaParse Extract Agentic against every other model

Qwen 3.8 27B against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, LlamaParse Extract Agentic or Qwen 3.8 27B?

LlamaParse Extract Agentic: 85.5 F1 against 83.8.

Which is cheaper, LlamaParse Extract Agentic or Qwen 3.8 27B?

Qwen 3.8 27B: $9.59 per 1,000 pages against $23.

Where does each one do better?

LlamaParse Extract Agentic: scanned & rotated, rotated & warped pages and handwritten. Qwen 3.8 27B: resume-builder templates and medium.