LlamaParse Extract Agentic Plus vs Qwen 3.8 27B: which is better at resume extraction?
LlamaParse Extract Agentic Plus leads Qwen 3.8 27B by 3.4 points (87.2 vs 83.8 F1). Cost per 1,000 pages: $54 vs $9.59. Median time per resume: 70 s vs 36 s.
LlamaParse Extract Agentic Plus wins on 169 of 300 resumes, Qwen 3.8 27B on 79, 52 tied.
87.16
LlamaParse Extract Agentic Plus
A · Document API
83.77
Qwen 3.8 27B
B · Vision LLM
LlamaParse Extract Agentic Plus is ahead by 3.39 points on these 300 resumes.
- Many entries 83A 85.0 · B 81.6+3.4
- Long bullet lists 101A 84.9 · B 80.8+4.2
- Split across pages 85A 85.3 · B 81.8+3.5
- Big skills list 60A 86.0 · B 82.9+3.2
- Custom sections 105A 85.1 · B 81.0+4.1
- Combined headings 37A 84.6 · B 83.7+0.9
- Promotions 88A 87.4 · B 83.2+4.2
- Partial dates 138A 87.0 · B 83.6+3.4
- Overlapping jobs 69A 84.1 · B 82.4+1.7
- Accented text 13A 92.0 · B 84.9+7.0
Side by side
| LlamaParse Extract Agentic Plus | Qwen 3.8 27B | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | LlamaIndex | Alibaba |
| Rank | 1 of 18 | 9 of 18 |
| F1 | 87.2 | 83.8 |
| Precision | 88.4 | 85.4 |
| Recall | 88.3 | 85.5 |
| Cost per 1,000 pages | $54 | $9.59 |
| Median time per resume | 70 s | 36 s |
| Resumes won | 169 | 79 |
LlamaParse Extract Agentic Plus in detailQwen 3.8 27B in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Agentic Plus | Qwen 3.8 27B | Gap |
|---|---|---|---|---|
| Handwritten (reading the page) | 9 | 67.8 | 51.6 | +16.2 |
| Scanned & rotated (source) | 19 | 92.8 | 78.4 | +14.3 |
| Rotated & warped pages (distractors) | 21 | 92.5 | 78.7 | +13.7 |
| Image only (reading the page) | 28 | 84.2 | 70.5 | +13.7 |
| Hidden text & prompt injections (distractors) | 14 | 93.2 | 82.4 | +10.8 |
| Typos kept on purpose (distractors) | 37 | 91.4 | 82.9 | +8.5 |
| Accented text (extraction challenges) | 13 | 92.0 | 84.9 | +7.0 |
| Two-column sidebar (layout) | 54 | 84.8 | 78.4 | +6.4 |
| Long (length) | 62 | 79.7 | 73.4 | +6.3 |
| Sidebar or grid (reading the page) | 82 | 86.8 | 81.8 | +5.0 |
| Content as images (distractors) | 8 | 93.9 | 89.5 | +4.4 |
| Long bullet lists (extraction challenges) | 101 | 84.9 | 80.8 | +4.2 |
| Section | Resumes | LlamaParse Extract Agentic Plus | Qwen 3.8 27B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.3 | 93.2 | +1.2 |
| Experience | 300 | 91.5 | 86.2 | +5.4 |
| Education | 297 | 93.3 | 87.2 | +6.1 |
| Summary | 290 | 84.8 | 81.7 | +3.1 |
| Certifications | 240 | 85.8 | 82.7 | +3.1 |
| Awards | 93 | 84.1 | 78.4 | +5.7 |
| Skills | 283 | 97.6 | 92.7 | +4.9 |
| Languages | 167 | 84.6 | 85.4 | −0.7 |
| Custom sections | 211 | 52.2 | 51.2 | +0.9 |
| Interests | 64 | 93.0 | 94.6 | −1.6 |
| Volunteering | 77 | 89.6 | 84.7 | +4.9 |
| Profiles | 35 | 73.3 | 72.5 | +0.8 |
| Projects | 78 | 87.0 | 85.5 | +1.5 |
| Publications | 52 | 85.5 | 77.2 | +8.3 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Agentic Plus | Qwen 3.8 27B | Gap |
|---|---|---|---|
| Senior ocularist and practice owner: Handwritten resume, six pages | 74.0 | 41.2 | +32.9 |
| senior Consultant - package Implementation: Handwritten resume | 78.1 | 46.5 | +31.6 |
| Deputy Head of Mission: Rotated scan with hidden identity text | 90.0 | 65.6 | +24.4 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 97.7 | 79.1 | +18.6 |
Which to pick
LlamaParse Extract Agentic Plus is more accurate. Qwen 3.8 27B costs 82% less for 3.4 fewer points.
LlamaParse Extract Agentic Plus does better on handwritten, scanned & rotated and rotated & warped pages. Qwen 3.8 27B does better on resume-builder templates.
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 3.5 35B
- LlamaParse Extract Agentic Plus vs Qwen 3.5 9B
- LlamaParse Extract Agentic Plus vs GLM 5.3 Flash
Qwen 3.8 27B against every other model
- Qwen 3.8 27B vs LlamaParse Extract Agentic
- Qwen 3.8 27B vs LlamaParse Extract Cost-Effective
- 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