LlamaParse Extract Cost-Effective vs Qwen 3.5 9B: which is better at resume extraction?
LlamaParse Extract Cost-Effective leads Qwen 3.5 9B by 7.5 points (83.5 vs 76.0 F1). Cost per 1,000 pages: $8.18 vs $1.31. Median time per resume: 29 s vs 138 s.
LlamaParse Extract Cost-Effective wins on 220 of 299 resumes, Qwen 3.5 9B on 64, 15 tied.
83.55
LlamaParse Extract Cost-Effective
A · Document API
76.03
Qwen 3.5 9B
B · Vision LLM
LlamaParse Extract Cost-Effective is ahead by 7.52 points on these 299 resumes.
- Many entries 82A 79.7 · B 73.9+5.8
- Long bullet lists 100A 80.4 · B 73.2+7.3
- Split across pages 84A 81.9 · B 73.4+8.5
- Big skills list 59A 84.3 · B 76.3+8.0
- Custom sections 104A 80.5 · B 73.0+7.5
- Combined headings 37A 82.8 · B 72.2+10.6
- Promotions 88A 82.9 · B 74.8+8.2
- Partial dates 138A 82.5 · B 75.6+6.9
- Overlapping jobs 69A 79.7 · B 72.2+7.6
- Accented text 13A 87.0 · B 83.7+3.3
Side by side
| LlamaParse Extract Cost-Effective | Qwen 3.5 9B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 10 of 18 | 15 of 18 |
| F1 | 83.5 | 76.0 |
| Precision | 85.1 | 78.9 |
| Recall | 85.3 | 80.3 |
| Cost per 1,000 pages | $8.18 | $1.31 |
| Median time per resume | 29 s | 138 s |
| Resumes won | 220 | 64 |
LlamaParse Extract Cost-Effective in detailQwen 3.5 9B in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Cost-Effective | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 90.4 | 64.5 | +25.8 |
| Rotated & warped pages (distractors) | 21 | 89.6 | 66.5 | +23.1 |
| Hidden text & prompt injections (distractors) | 14 | 90.5 | 70.2 | +20.4 |
| Typos kept on purpose (distractors) | 37 | 88.0 | 72.2 | +15.8 |
| Image only (reading the page) | 28 | 76.3 | 61.2 | +15.1 |
| Two-column sidebar (layout) | 54 | 82.3 | 69.7 | +12.6 |
| Sidebar or grid (reading the page) | 82 | 84.3 | 73.5 | +10.8 |
| Combined headings (extraction challenges) | 37 | 82.8 | 72.2 | +10.6 |
| Three-column (layout) | 20 | 85.9 | 75.8 | +10.1 |
| Short (length) | 148 | 87.7 | 78.1 | +9.6 |
| Busy page (noise) | 18 | 76.9 | 67.6 | +9.3 |
| Split across pages (extraction challenges) | 84 | 81.9 | 73.4 | +8.5 |
| Section | Resumes | LlamaParse Extract Cost-Effective | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Contact details | 299 | 93.6 | 92.6 | +1.0 |
| Experience | 299 | 84.5 | 77.2 | +7.3 |
| Education | 296 | 87.6 | 80.8 | +6.8 |
| Summary | 289 | 81.7 | 77.9 | +3.7 |
| Certifications | 245 | 82.4 | 74.7 | +7.7 |
| Awards | 92 | 84.0 | 55.2 | +28.8 |
| Skills | 285 | 94.3 | 83.2 | +11.1 |
| Languages | 167 | 82.2 | 80.0 | +2.2 |
| Custom sections | 214 | 49.0 | 36.4 | +12.6 |
| Interests | 64 | 92.1 | 84.3 | +7.8 |
| Volunteering | 77 | 87.4 | 80.2 | +7.1 |
| Profiles | 36 | 71.3 | 51.3 | +20.0 |
| Projects | 77 | 83.3 | 75.5 | +7.8 |
| Publications | 51 | 72.2 | 76.3 | −4.1 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Cost-Effective | Qwen 3.5 9B | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 88.9 | 65.0 | +23.8 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 72.4 | 54.9 | +17.5 |
| Senior Controls Engineer: Five custom sections | 80.8 | 65.2 | +15.6 |
| Head of Developer Experience (Internal title: Jedi Master of Analytics) : Unusual job titles | 92.7 | 77.2 | +15.5 |
Which to pick
LlamaParse Extract Cost-Effective is more accurate. Qwen 3.5 9B costs 84% less for 7.5 fewer points.
LlamaParse Extract Cost-Effective does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections. Qwen 3.5 9B does better on handwritten.
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 35B
- LlamaParse Extract Cost-Effective 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 Agentic
- 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