LlamaParse Extract Cost-Effective vs Qwen 3.8 27B: which is better at resume extraction?
Qwen 3.8 27B leads LlamaParse Extract Cost-Effective by 0.3 points (83.8 vs 83.5 F1). Cost per 1,000 pages: $8.18 vs $9.59. Median time per resume: 29 s vs 36 s.
LlamaParse Extract Cost-Effective wins on 117 of 300 resumes, Qwen 3.8 27B on 146, 37 tied.
83.52
LlamaParse Extract Cost-Effective
A · Document API
83.77
Qwen 3.8 27B
B · Vision LLM
Qwen 3.8 27B is ahead by 0.25 points on these 300 resumes.
- Many entries 83A 79.6 · B 81.6−2.0
- Long bullet lists 101A 80.4 · B 80.8−0.4
- Split across pages 85A 81.8 · B 81.8−0.0
- Big skills list 60A 84.1 · B 82.9+1.3
- Custom sections 105A 80.4 · B 81.0−0.6
- Combined headings 37A 82.8 · B 83.7−0.9
- Promotions 88A 82.9 · B 83.2−0.3
- Partial dates 138A 82.5 · B 83.6−1.1
- Overlapping jobs 69A 79.7 · B 82.4−2.6
- Accented text 13A 87.0 · B 84.9+2.1
Side by side
| LlamaParse Extract Cost-Effective | Qwen 3.8 27B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 10 of 18 | 9 of 18 |
| F1 | 83.5 | 83.8 |
| Precision | 85.1 | 85.4 |
| Recall | 85.3 | 85.5 |
| Cost per 1,000 pages | $8.18 | $9.59 |
| Median time per resume | 29 s | 36 s |
| Resumes won | 117 | 146 |
LlamaParse Extract Cost-Effective in detailQwen 3.8 27B in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Cost-Effective | Qwen 3.8 27B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 90.4 | 78.4 | +11.9 |
| Rotated & warped pages (distractors) | 21 | 89.6 | 78.7 | +10.9 |
| Hidden text & prompt injections (distractors) | 14 | 90.5 | 82.4 | +8.1 |
| Resume-builder templates (source) | 10 | 80.3 | 86.7 | −6.4 |
| Image only (reading the page) | 28 | 76.3 | 70.5 | +5.8 |
| Typos kept on purpose (distractors) | 37 | 88.0 | 82.9 | +5.1 |
| Two-column sidebar (layout) | 54 | 82.3 | 78.4 | +3.9 |
| Busy page (noise) | 18 | 76.9 | 80.4 | −3.4 |
| Overlapping jobs (extraction challenges) | 69 | 79.7 | 82.4 | −2.6 |
| Wording traps (distractors) | 16 | 85.0 | 87.6 | −2.6 |
| Medium (length) | 90 | 83.0 | 85.5 | −2.5 |
| Sidebar or grid (reading the page) | 82 | 84.3 | 81.8 | +2.5 |
| Section | Resumes | LlamaParse Extract Cost-Effective | Qwen 3.8 27B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 93.6 | 93.2 | +0.5 |
| Experience | 300 | 84.5 | 86.2 | −1.6 |
| Education | 297 | 87.6 | 87.2 | +0.4 |
| Summary | 290 | 81.7 | 81.7 | +0.0 |
| Certifications | 246 | 82.5 | 82.7 | −0.2 |
| Awards | 93 | 84.1 | 78.4 | +5.7 |
| Skills | 286 | 94.3 | 92.7 | +1.6 |
| Languages | 167 | 82.2 | 85.4 | −3.1 |
| Custom sections | 215 | 48.8 | 51.2 | −2.5 |
| Interests | 64 | 92.1 | 94.6 | −2.5 |
| Volunteering | 77 | 87.4 | 84.7 | +2.7 |
| Profiles | 37 | 69.4 | 72.5 | −3.2 |
| Projects | 78 | 82.7 | 85.5 | −2.8 |
| Publications | 51 | 72.2 | 77.2 | −5.0 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Cost-Effective | Qwen 3.8 27B | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 88.9 | 65.6 | +23.3 |
| Senior Game Designer: Game designer's Canva resume | 55.0 | 74.0 | −19.0 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 72.4 | 88.5 | −16.2 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 63.1 | 79.1 | −16.0 |
Which to pick
Qwen 3.8 27B is more accurate. LlamaParse Extract Cost-Effective costs 15% less for 0.3 fewer points.
LlamaParse Extract Cost-Effective does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections. Qwen 3.8 27B does better on resume-builder templates, busy page and overlapping jobs.
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 3.5 35B
- LlamaParse Extract Cost-Effective vs Qwen 3.5 9B
- LlamaParse Extract Cost-Effective vs GLM 5.3 Flash
Qwen 3.8 27B against every other model
- Qwen 3.8 27B vs LlamaParse Extract Agentic Plus
- Qwen 3.8 27B vs LlamaParse Extract Agentic
- Qwen 3.8 27B vs Reducto Deep Extract
- Qwen 3.8 27B vs Reducto Extract
- Qwen 3.8 27B vs Extend Max Context
- Qwen 3.8 27B vs Extend Extract
- Qwen 3.8 27B vs GPT-5.6
- Qwen 3.8 27B vs GPT-5.5
- Qwen 3.8 27B vs GPT-5.4 Nano
- Qwen 3.8 27B vs Claude Opus 4.8
- Qwen 3.8 27B vs Gemini 3.5 Flash
- Qwen 3.8 27B vs Gemma 4 26B
- Qwen 3.8 27B vs Qwen 3.8 Flash
- Qwen 3.8 27B vs Qwen 3.5 35B
- Qwen 3.8 27B vs Qwen 3.5 9B
- Qwen 3.8 27B 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