Qwen 3.5 9B vs Reducto Deep Extract: which is better at resume extraction?
Reducto Deep Extract leads Qwen 3.5 9B by 9.5 points (85.6 vs 76.0 F1). Cost per 1,000 pages: $1.31 vs $40. Median time per resume: 138 s vs 65 s.
Qwen 3.5 9B wins on 59 of 299 resumes, Reducto Deep Extract on 232, 8 tied.
76.03
Qwen 3.5 9B
A · Vision LLM
85.60
Reducto Deep Extract
B · Document API
Reducto Deep Extract is ahead by 9.57 points on these 299 resumes.
- Many entries 82A 73.9 · B 84.5−10.6
- Long bullet lists 100A 73.2 · B 84.6−11.4
- Split across pages 84A 73.4 · B 84.3−10.9
- Big skills list 59A 76.3 · B 86.0−9.7
- Custom sections 104A 73.0 · B 82.7−9.7
- Combined headings 37A 72.2 · B 82.7−10.5
- Promotions 88A 74.8 · B 86.0−11.2
- Partial dates 138A 75.6 · B 85.2−9.6
- Overlapping jobs 69A 72.2 · B 85.9−13.7
- Accented text 13A 83.7 · B 85.5−1.7
Side by side
| Qwen 3.5 9B | Reducto Deep Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | Alibaba | Reducto |
| Rank | 15 of 18 | 2 of 18 |
| F1 | 76.0 | 85.6 |
| Precision | 78.9 | 87.5 |
| Recall | 80.3 | 87.3 |
| Cost per 1,000 pages | $1.31 | $40 |
| Median time per resume | 138 s | 65 s |
| Resumes won | 59 | 232 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Qwen 3.5 9B | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 64.5 | 90.1 | −25.6 |
| Rotated & warped pages (distractors) | 21 | 66.5 | 89.3 | −22.8 |
| Hidden text & prompt injections (distractors) | 14 | 70.2 | 90.1 | −19.9 |
| Busy page (noise) | 18 | 67.6 | 83.6 | −16.0 |
| Typos kept on purpose (distractors) | 37 | 72.2 | 87.9 | −15.7 |
| Image only (reading the page) | 28 | 61.2 | 76.4 | −15.2 |
| Two-column sidebar (layout) | 54 | 69.7 | 83.8 | −14.1 |
| Overlapping jobs (extraction challenges) | 69 | 72.2 | 85.9 | −13.7 |
| References (noise) | 55 | 77.6 | 90.2 | −12.6 |
| Sidebar or grid (reading the page) | 82 | 73.5 | 85.2 | −11.7 |
| Photo (reading the page) | 45 | 74.9 | 86.4 | −11.5 |
| Long bullet lists (extraction challenges) | 100 | 73.2 | 84.6 | −11.4 |
| Section | Resumes | Qwen 3.5 9B | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Contact details | 299 | 92.6 | 94.3 | −1.8 |
| Experience | 299 | 77.2 | 90.6 | −13.4 |
| Education | 296 | 80.8 | 92.0 | −11.2 |
| Summary | 290 | 77.9 | 85.1 | −7.2 |
| Certifications | 246 | 74.7 | 81.3 | −6.6 |
| Awards | 127 | 55.2 | 79.2 | −24.0 |
| Skills | 293 | 83.2 | 94.3 | −11.0 |
| Languages | 172 | 80.0 | 81.8 | −1.8 |
| Custom sections | 214 | 36.4 | 51.3 | −14.9 |
| Interests | 68 | 84.3 | 93.8 | −9.5 |
| Volunteering | 80 | 80.2 | 89.5 | −9.3 |
| Profiles | 38 | 51.3 | 68.7 | −17.4 |
| Projects | 79 | 75.5 | 89.1 | −13.6 |
| Publications | 53 | 76.3 | 79.3 | −3.0 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Qwen 3.5 9B | Reducto Deep Extract | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 65.0 | 89.2 | −24.1 |
| Senior Controls Engineer: Five custom sections | 65.2 | 88.0 | −22.8 |
| Senior Manufacturing Engineer: Third-person prose, no bullets | 71.4 | 93.9 | −22.5 |
| Lead Respiratory Therapist (Adult ICU): Long resume, 34 entries | 69.4 | 88.9 | −19.4 |
Which to pick
Reducto Deep Extract is more accurate. Qwen 3.5 9B costs 97% less for 9.5 fewer points.
Qwen 3.5 9B does better on handwritten and resume-builder templates. Reducto Deep Extract does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
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 LlamaParse Extract Cost-Effective
- 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
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 35B
- 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