LlamaParse Extract Agentic Plus vs Qwen 3.5 35B: which is better at resume extraction?
LlamaParse Extract Agentic Plus leads Qwen 3.5 35B by 9.2 points (87.2 vs 77.9 F1). Cost per 1,000 pages: $54 vs $3.91. Median time per resume: 70 s vs 78 s.
LlamaParse Extract Agentic Plus wins on 242 of 300 resumes, Qwen 3.5 35B on 50, 8 tied.
87.16
LlamaParse Extract Agentic Plus
A · Document API
77.95
Qwen 3.5 35B
B · Vision LLM
LlamaParse Extract Agentic Plus is ahead by 9.21 points on these 300 resumes.
- Many entries 83A 85.0 · B 78.9+6.1
- Long bullet lists 101A 84.9 · B 76.3+8.6
- Split across pages 85A 85.3 · B 76.5+8.9
- Big skills list 60A 86.0 · B 76.6+9.4
- Custom sections 105A 85.1 · B 77.0+8.1
- Combined headings 37A 84.6 · B 74.6+10.0
- Promotions 88A 87.4 · B 76.7+10.7
- Partial dates 138A 87.0 · B 78.9+8.1
- Overlapping jobs 69A 84.1 · B 76.2+7.9
- Accented text 13A 92.0 · B 80.4+11.5
Side by side
| LlamaParse Extract Agentic Plus | Qwen 3.5 35B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 1 of 18 | 14 of 18 |
| F1 | 87.2 | 77.9 |
| Precision | 88.4 | 78.8 |
| Recall | 88.3 | 83.7 |
| Cost per 1,000 pages | $54 | $3.91 |
| Median time per resume | 70 s | 78 s |
| Resumes won | 242 | 50 |
LlamaParse Extract Agentic Plus in detailQwen 3.5 35B in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Agentic Plus | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 92.8 | 75.3 | +17.5 |
| Rotated & warped pages (distractors) | 21 | 92.5 | 76.5 | +15.9 |
| Handwritten (reading the page) | 9 | 67.8 | 52.7 | +15.1 |
| Image only (reading the page) | 28 | 84.2 | 69.7 | +14.5 |
| Hidden text & prompt injections (distractors) | 14 | 93.2 | 79.2 | +14.0 |
| Two-column sidebar (layout) | 54 | 84.8 | 71.5 | +13.2 |
| Two-column (layout) | 23 | 90.3 | 77.4 | +12.9 |
| Three-column (layout) | 20 | 87.6 | 75.6 | +12.0 |
| Sidebar or grid (reading the page) | 82 | 86.8 | 74.8 | +12.0 |
| Accented text (extraction challenges) | 13 | 92.0 | 80.4 | +11.5 |
| Typos kept on purpose (distractors) | 37 | 91.4 | 80.4 | +11.0 |
| Busy page (noise) | 18 | 82.8 | 71.8 | +11.0 |
| Section | Resumes | LlamaParse Extract Agentic Plus | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.3 | 92.1 | +2.2 |
| Experience | 300 | 91.5 | 79.3 | +12.3 |
| Education | 297 | 93.3 | 81.8 | +11.5 |
| Summary | 290 | 84.8 | 80.4 | +4.4 |
| Certifications | 240 | 85.8 | 79.1 | +6.7 |
| Awards | 93 | 84.1 | 61.9 | +22.2 |
| Skills | 283 | 97.6 | 87.8 | +9.7 |
| Languages | 167 | 84.6 | 79.4 | +5.2 |
| Custom sections | 211 | 52.2 | 40.2 | +12.0 |
| Interests | 64 | 93.0 | 89.7 | +3.3 |
| Volunteering | 77 | 89.6 | 83.1 | +6.4 |
| Profiles | 35 | 73.3 | 65.8 | +7.5 |
| Projects | 78 | 87.0 | 76.7 | +10.2 |
| Publications | 52 | 85.5 | 75.0 | +10.6 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Agentic Plus | Qwen 3.5 35B | Gap |
|---|---|---|---|
| Senior ocularist and practice owner: Handwritten resume, six pages | 74.0 | 38.5 | +35.5 |
| senior Consultant - package Implementation: Handwritten resume | 78.1 | 59.2 | +18.8 |
| Senior Customer Service Representative: Busy Canva page | 87.5 | 70.7 | +16.8 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 97.7 | 84.1 | +13.6 |
Which to pick
LlamaParse Extract Agentic Plus is more accurate. Qwen 3.5 35B costs 93% less for 9.2 fewer points.
LlamaParse Extract Agentic Plus does better on scanned & rotated, rotated & warped pages and handwritten.
LlamaParse Extract Agentic Plus against every other model
- LlamaParse Extract Agentic Plus vs LlamaParse Extract Agentic
- LlamaParse Extract Agentic Plus vs LlamaParse Extract Cost-Effective
- LlamaParse Extract Agentic Plus vs Reducto Deep Extract
- LlamaParse Extract Agentic Plus vs Reducto Extract
- LlamaParse Extract Agentic Plus vs Extend Max Context
- LlamaParse Extract Agentic Plus vs Extend Extract
- LlamaParse Extract Agentic Plus vs GPT-5.6
- LlamaParse Extract Agentic Plus vs GPT-5.5
- LlamaParse Extract Agentic Plus vs GPT-5.4 Nano
- LlamaParse Extract Agentic Plus vs Claude Opus 4.8
- LlamaParse Extract Agentic Plus vs Gemini 3.5 Flash
- LlamaParse Extract Agentic Plus vs Gemma 4 26B
- LlamaParse Extract Agentic Plus vs Qwen 3.8 Flash
- LlamaParse Extract Agentic Plus vs Qwen 3.8 27B
- LlamaParse Extract Agentic Plus vs Qwen 3.5 9B
- LlamaParse Extract Agentic Plus vs GLM 5.3 Flash
Qwen 3.5 35B against every other model
- Qwen 3.5 35B vs LlamaParse Extract Agentic
- 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