LlamaParse Extract Agentic Plus vs Qwen 3.5 9B: which is better at resume extraction?
LlamaParse Extract Agentic Plus leads Qwen 3.5 9B by 11.1 points (87.2 vs 76.0 F1). Cost per 1,000 pages: $54 vs $1.31. Median time per resume: 70 s vs 138 s.
LlamaParse Extract Agentic Plus wins on 252 of 299 resumes, Qwen 3.5 9B on 33, 14 tied.
87.20
LlamaParse Extract Agentic Plus
A · Document API
76.03
Qwen 3.5 9B
B · Vision LLM
LlamaParse Extract Agentic Plus is ahead by 11.17 points on these 299 resumes.
- Many entries 82A 85.2 · B 73.9+11.3
- Long bullet lists 100A 85.1 · B 73.2+11.9
- Split across pages 84A 85.5 · B 73.4+12.1
- Big skills list 59A 86.2 · B 76.3+9.9
- Custom sections 104A 85.2 · B 73.0+12.2
- Combined headings 37A 84.6 · B 72.2+12.4
- Promotions 88A 87.4 · B 74.8+12.6
- Partial dates 138A 87.0 · B 75.6+11.4
- Overlapping jobs 69A 84.1 · B 72.2+11.9
- Accented text 13A 92.0 · B 83.7+8.3
Side by side
| LlamaParse Extract Agentic Plus | Qwen 3.5 9B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 1 of 18 | 15 of 18 |
| F1 | 87.2 | 76.0 |
| Precision | 88.4 | 78.9 |
| Recall | 88.3 | 80.3 |
| Cost per 1,000 pages | $54 | $1.31 |
| Median time per resume | 70 s | 138 s |
| Resumes won | 252 | 33 |
LlamaParse Extract Agentic Plus in detailQwen 3.5 9B in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Agentic Plus | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 92.8 | 64.5 | +28.3 |
| Rotated & warped pages (distractors) | 21 | 92.5 | 66.5 | +26.0 |
| Hidden text & prompt injections (distractors) | 14 | 93.2 | 70.2 | +23.0 |
| Image only (reading the page) | 28 | 84.2 | 61.2 | +23.0 |
| Typos kept on purpose (distractors) | 37 | 91.4 | 72.2 | +19.2 |
| Handwritten (reading the page) | 9 | 67.8 | 50.6 | +17.2 |
| Busy page (noise) | 18 | 82.8 | 67.6 | +15.2 |
| Two-column sidebar (layout) | 54 | 84.8 | 69.7 | +15.1 |
| Sidebar or grid (reading the page) | 82 | 86.8 | 73.5 | +13.3 |
| Photo (reading the page) | 45 | 88.1 | 74.9 | +13.2 |
| Repeated header (noise) | 67 | 89.3 | 76.4 | +12.8 |
| Promotions (extraction challenges) | 88 | 87.4 | 74.8 | +12.6 |
| Section | Resumes | LlamaParse Extract Agentic Plus | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Contact details | 299 | 94.3 | 92.6 | +1.8 |
| Experience | 299 | 91.5 | 77.2 | +14.3 |
| Education | 296 | 93.3 | 80.8 | +12.5 |
| Summary | 289 | 84.8 | 77.9 | +6.8 |
| Certifications | 239 | 85.7 | 74.7 | +11.0 |
| Awards | 92 | 85.0 | 55.2 | +29.9 |
| Skills | 282 | 97.6 | 83.2 | +14.3 |
| Languages | 167 | 84.6 | 80.0 | +4.6 |
| Custom sections | 210 | 52.3 | 36.4 | +15.9 |
| Interests | 64 | 93.0 | 84.3 | +8.7 |
| Volunteering | 77 | 89.6 | 80.2 | +9.4 |
| Profiles | 34 | 72.5 | 51.3 | +21.2 |
| Projects | 77 | 87.6 | 75.5 | +12.2 |
| Publications | 52 | 85.5 | 76.3 | +9.2 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Agentic Plus | Qwen 3.5 9B | Gap |
|---|---|---|---|
| Senior ocularist and practice owner: Handwritten resume, six pages | 74.0 | 43.7 | +30.3 |
| senior Consultant - package Implementation: Handwritten resume | 78.1 | 48.7 | +29.4 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 83.9 | 54.9 | +29.0 |
| Deputy Head of Mission: Rotated scan with hidden identity text | 90.0 | 65.0 | +25.0 |
Which to pick
LlamaParse Extract Agentic Plus is more accurate. Qwen 3.5 9B costs 98% less for 11.1 fewer points.
LlamaParse Extract Agentic Plus does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
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 35B
- LlamaParse Extract Agentic Plus vs GLM 5.3 Flash
Qwen 3.5 9B against every other model
- Qwen 3.5 9B vs LlamaParse Extract Agentic
- Qwen 3.5 9B vs LlamaParse Extract Cost-Effective
- Qwen 3.5 9B vs Reducto Deep Extract
- Qwen 3.5 9B vs Reducto Extract
- Qwen 3.5 9B vs Extend Max Context
- Qwen 3.5 9B vs Extend Extract
- Qwen 3.5 9B vs GPT-5.6
- Qwen 3.5 9B vs GPT-5.5
- Qwen 3.5 9B vs GPT-5.4 Nano
- Qwen 3.5 9B vs Claude Opus 4.8
- Qwen 3.5 9B vs Gemini 3.5 Flash
- Qwen 3.5 9B vs Gemma 4 26B
- Qwen 3.5 9B vs Qwen 3.8 Flash
- Qwen 3.5 9B vs Qwen 3.8 27B
- Qwen 3.5 9B vs Qwen 3.5 35B
- Qwen 3.5 9B 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