LlamaParse Extract Cost-Effective vs Qwen 3.5 35B: which is better at resume extraction?
LlamaParse Extract Cost-Effective leads Qwen 3.5 35B by 5.6 points (83.5 vs 77.9 F1). Cost per 1,000 pages: $8.18 vs $3.91. Median time per resume: 29 s vs 78 s.
LlamaParse Extract Cost-Effective wins on 195 of 300 resumes, Qwen 3.5 35B on 96, 9 tied.
83.52
LlamaParse Extract Cost-Effective
A · Document API
77.95
Qwen 3.5 35B
B · Vision LLM
LlamaParse Extract Cost-Effective is ahead by 5.57 points on these 300 resumes.
- Many entries 83A 79.6 · B 78.9+0.7
- Long bullet lists 101A 80.4 · B 76.3+4.0
- Split across pages 85A 81.8 · B 76.5+5.3
- Big skills list 60A 84.1 · B 76.6+7.5
- Custom sections 105A 80.4 · B 77.0+3.4
- Combined headings 37A 82.8 · B 74.6+8.2
- Promotions 88A 82.9 · B 76.7+6.2
- Partial dates 138A 82.5 · B 78.9+3.6
- Overlapping jobs 69A 79.7 · B 76.2+3.5
- Accented text 13A 87.0 · B 80.4+6.6
Side by side
| LlamaParse Extract Cost-Effective | Qwen 3.5 35B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 10 of 18 | 14 of 18 |
| F1 | 83.5 | 77.9 |
| Precision | 85.1 | 78.8 |
| Recall | 85.3 | 83.7 |
| Cost per 1,000 pages | $8.18 | $3.91 |
| Median time per resume | 29 s | 78 s |
| Resumes won | 195 | 96 |
LlamaParse Extract Cost-Effective in detailQwen 3.5 35B in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Cost-Effective | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 90.4 | 75.3 | +15.0 |
| Rotated & warped pages (distractors) | 21 | 89.6 | 76.5 | +13.1 |
| Hidden text & prompt injections (distractors) | 14 | 90.5 | 79.2 | +11.3 |
| Two-column sidebar (layout) | 54 | 82.3 | 71.5 | +10.7 |
| Three-column (layout) | 20 | 85.9 | 75.6 | +10.3 |
| Sidebar or grid (reading the page) | 82 | 84.3 | 74.8 | +9.5 |
| Two-column (layout) | 23 | 86.7 | 77.4 | +9.3 |
| Combined headings (extraction challenges) | 37 | 82.8 | 74.6 | +8.2 |
| Short (length) | 148 | 87.7 | 79.8 | +7.9 |
| Typos kept on purpose (distractors) | 37 | 88.0 | 80.4 | +7.6 |
| Big skills list (extraction challenges) | 60 | 84.1 | 76.6 | +7.5 |
| Everyday resumes (source) | 212 | 84.6 | 77.7 | +6.9 |
| Section | Resumes | LlamaParse Extract Cost-Effective | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 93.6 | 92.1 | +1.5 |
| Experience | 300 | 84.5 | 79.3 | +5.3 |
| Education | 297 | 87.6 | 81.8 | +5.8 |
| Summary | 290 | 81.7 | 80.4 | +1.3 |
| Certifications | 246 | 82.5 | 79.1 | +3.4 |
| Awards | 93 | 84.1 | 61.9 | +22.3 |
| Skills | 286 | 94.3 | 87.8 | +6.5 |
| Languages | 167 | 82.2 | 79.4 | +2.8 |
| Custom sections | 215 | 48.8 | 40.2 | +8.6 |
| Interests | 64 | 92.1 | 89.7 | +2.3 |
| Volunteering | 77 | 87.4 | 83.1 | +4.2 |
| Profiles | 37 | 69.4 | 65.8 | +3.6 |
| Projects | 78 | 82.7 | 76.7 | +5.9 |
| Publications | 51 | 72.2 | 75.0 | −2.7 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Cost-Effective | Qwen 3.5 35B | Gap |
|---|---|---|---|
| Senior Data Scientist (Lead): Fifty skills, seven pages | 63.1 | 84.1 | −21.0 |
| senior Consultant - package Implementation: Handwritten resume | 44.1 | 59.2 | −15.1 |
| Senior ocularist and practice owner: Handwritten resume, six pages | 51.4 | 38.5 | +12.9 |
| Senior Game Designer: Game designer's Canva resume | 55.0 | 66.8 | −11.8 |
Which to pick
LlamaParse Extract Cost-Effective is more accurate. Qwen 3.5 35B costs 52% less for 5.6 fewer points.
LlamaParse Extract Cost-Effective does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections. Qwen 3.5 35B does better on handwritten, content as images and expert-built (canva / latex).
LlamaParse Extract Cost-Effective against every other model
- LlamaParse Extract Cost-Effective vs LlamaParse Extract Agentic Plus
- LlamaParse Extract Cost-Effective vs LlamaParse Extract Agentic
- LlamaParse Extract Cost-Effective vs Reducto Deep Extract
- LlamaParse Extract Cost-Effective vs Reducto Extract
- LlamaParse Extract Cost-Effective vs Extend Max Context
- LlamaParse Extract Cost-Effective vs Extend Extract
- LlamaParse Extract Cost-Effective vs GPT-5.6
- LlamaParse Extract Cost-Effective vs GPT-5.5
- LlamaParse Extract Cost-Effective vs GPT-5.4 Nano
- LlamaParse Extract Cost-Effective vs Claude Opus 4.8
- LlamaParse Extract Cost-Effective vs Gemini 3.5 Flash
- LlamaParse Extract Cost-Effective vs Gemma 4 26B
- LlamaParse Extract Cost-Effective vs Qwen 3.8 Flash
- LlamaParse Extract Cost-Effective vs Qwen 3.8 27B
- LlamaParse Extract Cost-Effective vs Qwen 3.5 9B
- LlamaParse Extract Cost-Effective 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 Agentic
- 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