Skip to content
vs

LlamaParse Extract Agentic vs Qwen 3.5 9B: which is better at resume extraction?

LlamaParse Extract Agentic leads Qwen 3.5 9B by 9.5 points (85.5 vs 76.0 F1). Cost per 1,000 pages: $23 vs $1.31. Median time per resume: 55 s vs 138 s.

LlamaParse Extract Agentic wins on 237 of 299 resumes, Qwen 3.5 9B on 47, 15 tied.

85.58

LlamaParse Extract Agentic

A · Document API

+9.55A − B, points of F1

76.03

Qwen 3.5 9B

B · Vision LLM

A better on 237level on 15B better on 47

LlamaParse Extract Agentic is ahead by 9.55 points on these 299 resumes.

  • Many entries 82A 83.1 · B 73.9+9.2
  • Long bullet lists 100A 83.2 · B 73.2+10.0
  • Split across pages 84A 83.9 · B 73.4+10.5
  • Big skills list 59A 83.9 · B 76.3+7.6
  • Custom sections 104A 82.6 · B 73.0+9.6
  • Combined headings 37A 83.2 · B 72.2+11.0
  • Promotions 88A 85.5 · B 74.8+10.8
  • Partial dates 138A 85.6 · B 75.6+10.0
  • Overlapping jobs 69A 83.5 · B 72.2+11.3
  • Accented text 13A 91.1 · B 83.7+7.4

Side by side

LlamaParse Extract Agentic vs Qwen 3.5 9B
LlamaParse Extract AgenticQwen 3.5 9B
TypeDocument APIVision LLM
MakerLlamaIndexAlibaba
Rank3 of 1815 of 18
F185.576.0
Precision86.878.9
Recall87.380.3
Cost per 1,000 pages$23$1.31
Median time per resume55 s138 s
Resumes won23747

LlamaParse Extract Agentic in detailQwen 3.5 9B in detail

Where each one wins

Where the two differ most.

LlamaParse Extract Agentic vs Qwen 3.5 9B by kind of resume
Kind of resume# of resumesLlamaParse Extract AgenticQwen 3.5 9BGap
Scanned & rotated (source)1991.664.5+27.1
Rotated & warped pages (distractors)2190.966.5+24.5
Hidden text & prompt injections (distractors)1491.670.2+21.4
Image only (reading the page)2881.561.2+20.3
Typos kept on purpose (distractors)3790.072.2+17.8
Busy page (noise)1883.567.6+16.0
Two-column sidebar (layout)5484.069.7+14.3
Handwritten (reading the page)963.550.6+12.9
Sidebar or grid (reading the page)8285.573.5+12.0
Overlapping jobs (extraction challenges)6983.572.2+11.3
Short (length)14889.478.1+11.2
Combined headings (extraction challenges)3783.272.2+11.0
LlamaParse Extract Agentic vs Qwen 3.5 9B by section
SectionResumesLlamaParse Extract AgenticQwen 3.5 9BGap
Contact details29994.692.6+2.0
Experience29989.577.2+12.4
Education29691.380.8+10.5
Summary28984.477.9+6.5
Certifications25180.974.7+6.2
Awards9280.155.2+24.9
Skills28595.183.2+11.8
Languages16784.280.0+4.1
Custom sections20752.236.4+15.8
Interests6493.084.3+8.7
Volunteering7787.780.2+7.4
Profiles3469.651.3+18.3
Projects7786.875.5+11.3
Publications5180.576.3+4.2

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 3.5 9B costs 94% less for 9.5 fewer points.

LlamaParse Extract Agentic does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.

LlamaParse Extract Agentic against every other model

Qwen 3.5 9B against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, LlamaParse Extract Agentic or Qwen 3.5 9B?

LlamaParse Extract Agentic: 85.5 F1 against 76.0.

Which is cheaper, LlamaParse Extract Agentic or Qwen 3.5 9B?

Qwen 3.5 9B: $1.31 per 1,000 pages against $23.

Where does each one do better?

LlamaParse Extract Agentic: scanned & rotated, rotated & warped pages and hidden text & prompt injections.