Qwen 3.5 35B vs Reducto Deep Extract: which is better at resume extraction?
Reducto Deep Extract leads Qwen 3.5 35B by 7.6 points (85.6 vs 77.9 F1). Cost per 1,000 pages: $3.91 vs $40. Median time per resume: 78 s vs 65 s.
Qwen 3.5 35B wins on 73 of 300 resumes, Reducto Deep Extract on 219, 8 tied.
77.95
Qwen 3.5 35B
A · Vision LLM
85.55
Reducto Deep Extract
B · Document API
Reducto Deep Extract is ahead by 7.60 points on these 300 resumes.
- Many entries 83A 78.9 · B 84.3−5.4
- Long bullet lists 101A 76.3 · B 84.5−8.2
- Split across pages 85A 76.5 · B 84.1−7.7
- Big skills list 60A 76.6 · B 85.8−9.2
- Custom sections 105A 77.0 · B 82.6−5.6
- Combined headings 37A 74.6 · B 82.7−8.1
- Promotions 88A 76.7 · B 86.0−9.3
- Partial dates 138A 78.9 · B 85.2−6.3
- Overlapping jobs 69A 76.2 · B 85.9−9.6
- Accented text 13A 80.4 · B 85.5−5.0
Side by side
| Qwen 3.5 35B | Reducto Deep Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | Alibaba | Reducto |
| Rank | 14 of 18 | 2 of 18 |
| F1 | 77.9 | 85.6 |
| Precision | 78.8 | 87.5 |
| Recall | 83.7 | 87.3 |
| Cost per 1,000 pages | $3.91 | $40 |
| Median time per resume | 78 s | 65 s |
| Resumes won | 73 | 219 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Qwen 3.5 35B | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 75.3 | 90.1 | −14.8 |
| Rotated & warped pages (distractors) | 21 | 76.5 | 89.3 | −12.7 |
| Two-column sidebar (layout) | 54 | 71.5 | 83.8 | −12.2 |
| Busy page (noise) | 18 | 71.8 | 83.6 | −11.8 |
| Hidden text & prompt injections (distractors) | 14 | 79.2 | 90.1 | −10.9 |
| Sidebar or grid (reading the page) | 82 | 74.8 | 85.2 | −10.5 |
| Three-column (layout) | 20 | 75.6 | 86.0 | −10.4 |
| Overlapping jobs (extraction challenges) | 69 | 76.2 | 85.9 | −9.6 |
| Two-column (layout) | 23 | 77.4 | 86.9 | −9.5 |
| Everyday resumes (source) | 212 | 77.7 | 87.2 | −9.5 |
| Promotions (extraction challenges) | 88 | 76.7 | 86.0 | −9.3 |
| Big skills list (extraction challenges) | 60 | 76.6 | 85.8 | −9.2 |
| Section | Resumes | Qwen 3.5 35B | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 92.1 | 94.2 | −2.1 |
| Experience | 300 | 79.3 | 90.6 | −11.3 |
| Education | 297 | 81.8 | 92.0 | −10.2 |
| Summary | 291 | 80.4 | 85.2 | −4.8 |
| Certifications | 251 | 79.1 | 81.4 | −2.3 |
| Awards | 116 | 61.9 | 79.4 | −17.5 |
| Skills | 294 | 87.8 | 93.9 | −6.1 |
| Languages | 175 | 79.4 | 81.8 | −2.4 |
| Custom sections | 236 | 40.2 | 51.3 | −11.1 |
| Interests | 66 | 89.7 | 93.8 | −4.0 |
| Volunteering | 80 | 83.1 | 89.5 | −6.4 |
| Profiles | 39 | 65.8 | 69.6 | −3.8 |
| Projects | 81 | 76.7 | 88.1 | −11.3 |
| Publications | 53 | 75.0 | 79.3 | −4.4 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Qwen 3.5 35B | Reducto Deep Extract | Gap |
|---|---|---|---|
| Senior Manufacturing Engineer: Third-person prose, no bullets | 74.3 | 93.9 | −19.5 |
| Creative Director: Accented text in a styled CV | 79.3 | 61.2 | +18.2 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 82.8 | 66.6 | +16.2 |
| Senior Game Designer: Game designer's Canva resume | 66.8 | 52.9 | +13.9 |
Which to pick
Reducto Deep Extract is more accurate. Qwen 3.5 35B costs 90% less for 7.6 fewer points.
Qwen 3.5 35B does better on handwritten, content as images and resume-builder templates. Reducto Deep Extract does better on scanned & rotated, rotated & warped pages and two-column sidebar.
Qwen 3.5 35B against every other model
- Qwen 3.5 35B vs LlamaParse Extract Agentic Plus
- Qwen 3.5 35B vs LlamaParse Extract Agentic
- Qwen 3.5 35B vs LlamaParse Extract Cost-Effective
- Qwen 3.5 35B vs Reducto Extract
- Qwen 3.5 35B vs Extend Max Context
- Qwen 3.5 35B vs Extend Extract
- Qwen 3.5 35B vs GPT-5.6
- Qwen 3.5 35B vs GPT-5.5
- Qwen 3.5 35B vs GPT-5.4 Nano
- Qwen 3.5 35B vs Claude Opus 4.8
- Qwen 3.5 35B vs Gemini 3.5 Flash
- Qwen 3.5 35B vs Gemma 4 26B
- Qwen 3.5 35B vs Qwen 3.8 Flash
- Qwen 3.5 35B vs Qwen 3.8 27B
- Qwen 3.5 35B vs Qwen 3.5 9B
- Qwen 3.5 35B vs GLM 5.3 Flash
Reducto Deep Extract against every other model
- Reducto Deep Extract vs LlamaParse Extract Agentic Plus
- Reducto Deep Extract vs LlamaParse Extract Agentic
- Reducto Deep Extract vs LlamaParse Extract Cost-Effective
- Reducto Deep Extract vs Reducto Extract
- Reducto Deep Extract vs Extend Max Context
- Reducto Deep Extract vs Extend Extract
- Reducto Deep Extract vs GPT-5.6
- Reducto Deep Extract vs GPT-5.5
- Reducto Deep Extract vs GPT-5.4 Nano
- Reducto Deep Extract vs Claude Opus 4.8
- Reducto Deep Extract vs Gemini 3.5 Flash
- Reducto Deep Extract vs Gemma 4 26B
- Reducto Deep Extract vs Qwen 3.8 Flash
- Reducto Deep Extract vs Qwen 3.8 27B
- Reducto Deep Extract vs Qwen 3.5 9B
- Reducto Deep Extract 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