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
76.03
Qwen 3.5 9B
B · Vision LLM
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 | Qwen 3.5 9B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 3 of 18 | 15 of 18 |
| F1 | 85.5 | 76.0 |
| Precision | 86.8 | 78.9 |
| Recall | 87.3 | 80.3 |
| Cost per 1,000 pages | $23 | $1.31 |
| Median time per resume | 55 s | 138 s |
| Resumes won | 237 | 47 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Agentic | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 91.6 | 64.5 | +27.1 |
| Rotated & warped pages (distractors) | 21 | 90.9 | 66.5 | +24.5 |
| Hidden text & prompt injections (distractors) | 14 | 91.6 | 70.2 | +21.4 |
| Image only (reading the page) | 28 | 81.5 | 61.2 | +20.3 |
| Typos kept on purpose (distractors) | 37 | 90.0 | 72.2 | +17.8 |
| Busy page (noise) | 18 | 83.5 | 67.6 | +16.0 |
| Two-column sidebar (layout) | 54 | 84.0 | 69.7 | +14.3 |
| Handwritten (reading the page) | 9 | 63.5 | 50.6 | +12.9 |
| Sidebar or grid (reading the page) | 82 | 85.5 | 73.5 | +12.0 |
| Overlapping jobs (extraction challenges) | 69 | 83.5 | 72.2 | +11.3 |
| Short (length) | 148 | 89.4 | 78.1 | +11.2 |
| Combined headings (extraction challenges) | 37 | 83.2 | 72.2 | +11.0 |
| Section | Resumes | LlamaParse Extract Agentic | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Contact details | 299 | 94.6 | 92.6 | +2.0 |
| Experience | 299 | 89.5 | 77.2 | +12.4 |
| Education | 296 | 91.3 | 80.8 | +10.5 |
| Summary | 289 | 84.4 | 77.9 | +6.5 |
| Certifications | 251 | 80.9 | 74.7 | +6.2 |
| Awards | 92 | 80.1 | 55.2 | +24.9 |
| Skills | 285 | 95.1 | 83.2 | +11.8 |
| Languages | 167 | 84.2 | 80.0 | +4.1 |
| Custom sections | 207 | 52.2 | 36.4 | +15.8 |
| Interests | 64 | 93.0 | 84.3 | +8.7 |
| Volunteering | 77 | 87.7 | 80.2 | +7.4 |
| Profiles | 34 | 69.6 | 51.3 | +18.3 |
| Projects | 77 | 86.8 | 75.5 | +11.3 |
| Publications | 51 | 80.5 | 76.3 | +4.2 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Agentic | Qwen 3.5 9B | Gap |
|---|---|---|---|
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 83.9 | 54.9 | +29.0 |
| Senior ocularist and practice owner: Handwritten resume, six pages | 70.4 | 43.7 | +26.7 |
| senior Consultant - package Implementation: Handwritten resume | 74.0 | 48.7 | +25.3 |
| Deputy Head of Mission: Rotated scan with hidden identity text | 89.5 | 65.0 | +24.5 |
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
- 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 35B
- LlamaParse Extract Agentic vs GLM 5.3 Flash
Qwen 3.5 9B against every other model
- Qwen 3.5 9B vs LlamaParse Extract Agentic Plus
- 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