Qwen 3.5 35B vs Reducto Extract: which is better at resume extraction?
Reducto Extract leads Qwen 3.5 35B by 3.7 points (81.7 vs 77.9 F1). Cost per 1,000 pages: $3.91 vs $20. Median time per resume: 78 s vs 16 s.
Qwen 3.5 35B wins on 111 of 300 resumes, Reducto Extract on 183, 6 tied.
77.95
Qwen 3.5 35B
A · Vision LLM
81.70
Reducto Extract
B · Document API
Reducto Extract is ahead by 3.75 points on these 300 resumes.
- Many entries 83A 78.9 · B 79.5−0.5
- Long bullet lists 101A 76.3 · B 80.2−3.9
- Split across pages 85A 76.5 · B 79.7−3.2
- Big skills list 60A 76.6 · B 83.2−6.6
- Custom sections 105A 77.0 · B 78.2−1.2
- Combined headings 37A 74.6 · B 80.2−5.6
- Promotions 88A 76.7 · B 82.8−6.1
- Partial dates 138A 78.9 · B 80.0−1.1
- Overlapping jobs 69A 76.2 · B 80.4−4.2
- Accented text 13A 80.4 · B 87.8−7.3
Side by side
| Qwen 3.5 35B | Reducto Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | Alibaba | Reducto |
| Rank | 14 of 18 | 12 of 18 |
| F1 | 77.9 | 81.7 |
| Precision | 78.8 | 83.7 |
| Recall | 83.7 | 84.0 |
| Cost per 1,000 pages | $3.91 | $20 |
| Median time per resume | 78 s | 16 s |
| Resumes won | 111 | 183 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Qwen 3.5 35B | Reducto Extract | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 75.3 | 89.9 | −14.6 |
| Handwritten (reading the page) | 9 | 52.7 | 39.4 | +13.4 |
| Rotated & warped pages (distractors) | 21 | 76.5 | 89.2 | −12.7 |
| Two-column sidebar (layout) | 54 | 71.5 | 81.6 | −10.1 |
| Hidden text & prompt injections (distractors) | 14 | 79.2 | 87.2 | −8.0 |
| Sidebar or grid (reading the page) | 82 | 74.8 | 82.1 | −7.3 |
| Accented text (extraction challenges) | 13 | 80.4 | 87.8 | −7.3 |
| Big skills list (extraction challenges) | 60 | 76.6 | 83.2 | −6.6 |
| Promotions (extraction challenges) | 88 | 76.7 | 82.8 | −6.1 |
| Typos kept on purpose (distractors) | 37 | 80.4 | 86.2 | −5.8 |
| Two-column (layout) | 23 | 77.4 | 83.2 | −5.8 |
| Combined headings (extraction challenges) | 37 | 74.6 | 80.2 | −5.6 |
| Section | Resumes | Qwen 3.5 35B | Reducto Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 92.1 | 93.4 | −1.3 |
| Experience | 300 | 79.3 | 84.0 | −4.7 |
| Education | 297 | 81.8 | 82.3 | −0.5 |
| Summary | 291 | 80.4 | 81.7 | −1.3 |
| Certifications | 251 | 79.1 | 81.3 | −2.2 |
| Awards | 116 | 61.9 | 73.5 | −11.6 |
| Skills | 294 | 87.8 | 93.0 | −5.2 |
| Languages | 175 | 79.4 | 84.3 | −4.9 |
| Custom sections | 236 | 40.2 | 44.4 | −4.2 |
| Interests | 66 | 89.7 | 92.8 | −3.1 |
| Volunteering | 80 | 83.1 | 82.7 | +0.4 |
| Profiles | 39 | 65.8 | 58.1 | +7.7 |
| Projects | 81 | 76.7 | 84.6 | −7.9 |
| Publications | 53 | 75.0 | 76.0 | −1.1 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Qwen 3.5 35B | Reducto Extract | Gap |
|---|---|---|---|
| Senior Data Scientist (Lead): Fifty skills, seven pages | 84.1 | 63.8 | +20.3 |
| senior Consultant - package Implementation: Handwritten resume | 59.2 | 40.0 | +19.2 |
| Senior Manufacturing Engineer: Third-person prose, no bullets | 74.3 | 92.4 | −18.1 |
| Head of Events & Public Space Operations: Table grid with emoji bullets | 88.2 | 72.9 | +15.2 |
Which to pick
Reducto Extract is more accurate. Qwen 3.5 35B costs 80% less for 3.7 fewer points.
Qwen 3.5 35B does better on handwritten, content as images and table grid. Reducto 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 Deep 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 Extract against every other model
- Reducto Extract vs LlamaParse Extract Agentic Plus
- Reducto Extract vs LlamaParse Extract Agentic
- Reducto Extract vs LlamaParse Extract Cost-Effective
- Reducto Extract vs Reducto Deep Extract
- Reducto Extract vs Extend Max Context
- Reducto Extract vs Extend Extract
- Reducto Extract vs GPT-5.6
- Reducto Extract vs GPT-5.5
- Reducto Extract vs GPT-5.4 Nano
- Reducto Extract vs Claude Opus 4.8
- Reducto Extract vs Gemini 3.5 Flash
- Reducto Extract vs Gemma 4 26B
- Reducto Extract vs Qwen 3.8 Flash
- Reducto Extract vs Qwen 3.8 27B
- Reducto Extract vs Qwen 3.5 9B
- Reducto 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