LlamaParse Extract Agentic vs Qwen 3.5 35B: which is better at resume extraction?
LlamaParse Extract Agentic leads Qwen 3.5 35B by 7.6 points (85.5 vs 77.9 F1). Cost per 1,000 pages: $23 vs $3.91. Median time per resume: 55 s vs 78 s.
LlamaParse Extract Agentic wins on 227 of 300 resumes, Qwen 3.5 35B on 65, 8 tied.
85.55
LlamaParse Extract Agentic
A · Document API
77.95
Qwen 3.5 35B
B · Vision LLM
LlamaParse Extract Agentic is ahead by 7.60 points on these 300 resumes.
- Many entries 83A 83.0 · B 78.9+4.1
- Long bullet lists 101A 83.1 · B 76.3+6.8
- Split across pages 85A 83.8 · B 76.5+7.3
- Big skills list 60A 83.7 · B 76.6+7.1
- Custom sections 105A 82.5 · B 77.0+5.5
- Combined headings 37A 83.2 · B 74.6+8.6
- Promotions 88A 85.5 · B 76.7+8.8
- Partial dates 138A 85.6 · B 78.9+6.7
- Overlapping jobs 69A 83.5 · B 76.2+7.3
- Accented text 13A 91.1 · B 80.4+10.7
Side by side
| LlamaParse Extract Agentic | Qwen 3.5 35B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 3 of 18 | 14 of 18 |
| F1 | 85.5 | 77.9 |
| Precision | 86.8 | 78.8 |
| Recall | 87.3 | 83.7 |
| Cost per 1,000 pages | $23 | $3.91 |
| Median time per resume | 55 s | 78 s |
| Resumes won | 227 | 65 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Agentic | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 91.6 | 75.3 | +16.3 |
| Rotated & warped pages (distractors) | 21 | 90.9 | 76.5 | +14.4 |
| Two-column sidebar (layout) | 54 | 84.0 | 71.5 | +12.5 |
| Hidden text & prompt injections (distractors) | 14 | 91.6 | 79.2 | +12.4 |
| Image only (reading the page) | 28 | 81.5 | 69.7 | +11.8 |
| Busy page (noise) | 18 | 83.5 | 71.8 | +11.8 |
| Two-column (layout) | 23 | 89.1 | 77.4 | +11.7 |
| Sidebar or grid (reading the page) | 82 | 85.5 | 74.8 | +10.7 |
| Accented text (extraction challenges) | 13 | 91.1 | 80.4 | +10.7 |
| Handwritten (reading the page) | 9 | 63.5 | 52.7 | +10.7 |
| Three-column (layout) | 20 | 85.4 | 75.6 | +9.8 |
| Typos kept on purpose (distractors) | 37 | 90.0 | 80.4 | +9.6 |
| Section | Resumes | LlamaParse Extract Agentic | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.5 | 92.1 | +2.4 |
| Experience | 300 | 89.6 | 79.3 | +10.3 |
| Education | 297 | 91.3 | 81.8 | +9.5 |
| Summary | 290 | 84.5 | 80.4 | +4.1 |
| Certifications | 252 | 80.9 | 79.1 | +1.9 |
| Awards | 93 | 80.3 | 61.9 | +18.4 |
| Skills | 286 | 95.1 | 87.8 | +7.2 |
| Languages | 167 | 84.2 | 79.4 | +4.8 |
| Custom sections | 208 | 52.1 | 40.2 | +11.9 |
| Interests | 64 | 93.0 | 89.7 | +3.2 |
| Volunteering | 77 | 87.7 | 83.1 | +4.5 |
| Profiles | 35 | 67.6 | 65.8 | +1.8 |
| Projects | 78 | 86.2 | 76.7 | +9.4 |
| Publications | 51 | 80.5 | 75.0 | +5.6 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Agentic | Qwen 3.5 35B | Gap |
|---|---|---|---|
| Senior ocularist and practice owner: Handwritten resume, six pages | 70.4 | 38.5 | +31.9 |
| senior Consultant - package Implementation: Handwritten resume | 74.0 | 59.2 | +14.7 |
| Senior Customer Service Representative: Busy Canva page | 81.9 | 70.7 | +11.1 |
| Head of Events & Public Space Operations: Table grid with emoji bullets | 98.4 | 88.2 | +10.2 |
Which to pick
LlamaParse Extract Agentic is more accurate. Qwen 3.5 35B costs 83% less for 7.6 fewer points.
LlamaParse Extract Agentic does better on scanned & rotated, rotated & warped pages and two-column sidebar.
LlamaParse Extract Agentic against every other model
- LlamaParse Extract Agentic vs LlamaParse Extract Agentic Plus
- LlamaParse Extract Agentic vs LlamaParse Extract Cost-Effective
- LlamaParse Extract Agentic vs Reducto Deep Extract
- LlamaParse Extract Agentic vs Reducto Extract
- LlamaParse Extract Agentic vs Extend Max Context
- LlamaParse Extract Agentic vs Extend Extract
- LlamaParse Extract Agentic vs GPT-5.6
- LlamaParse Extract Agentic vs GPT-5.5
- LlamaParse Extract Agentic vs GPT-5.4 Nano
- LlamaParse Extract Agentic vs Claude Opus 4.8
- LlamaParse Extract Agentic vs Gemini 3.5 Flash
- LlamaParse Extract Agentic vs Gemma 4 26B
- LlamaParse Extract Agentic vs Qwen 3.8 Flash
- LlamaParse Extract Agentic vs Qwen 3.8 27B
- LlamaParse Extract Agentic vs Qwen 3.5 9B
- LlamaParse Extract Agentic vs GLM 5.3 Flash
Qwen 3.5 35B against every other model
- Qwen 3.5 35B vs LlamaParse Extract Agentic Plus
- Qwen 3.5 35B vs LlamaParse Extract Cost-Effective
- Qwen 3.5 35B vs Reducto Deep Extract
- Qwen 3.5 35B vs Reducto Extract
- Qwen 3.5 35B vs Extend Max Context
- Qwen 3.5 35B vs Extend Extract
- Qwen 3.5 35B vs GPT-5.6
- Qwen 3.5 35B vs GPT-5.5
- Qwen 3.5 35B vs GPT-5.4 Nano
- Qwen 3.5 35B vs Claude Opus 4.8
- Qwen 3.5 35B vs Gemini 3.5 Flash
- Qwen 3.5 35B vs Gemma 4 26B
- Qwen 3.5 35B vs Qwen 3.8 Flash
- Qwen 3.5 35B vs Qwen 3.8 27B
- Qwen 3.5 35B vs Qwen 3.5 9B
- Qwen 3.5 35B vs GLM 5.3 Flash
Popular comparisons
- LlamaParse Extract Agentic Plus vs Reducto Deep Extract
- Extend Max Context vs Reducto Deep Extract
- Extend Max Context vs LlamaParse Extract Agentic Plus
- Claude Opus 4.8 vs GPT-5.6
- Gemini 3.5 Flash vs GPT-5.6
- Claude Opus 4.8 vs Gemini 3.5 Flash
- LlamaParse Extract Agentic vs LlamaParse Extract Agentic Plus
- Reducto Deep Extract vs Reducto Extract
- Gemma 4 26B vs Qwen 3.8 27B
- Document APIs vs vision LLMs