Qwen 3.5 9B vs Reducto Extract: which is better at resume extraction?
Reducto Extract leads Qwen 3.5 9B by 5.7 points (81.7 vs 76.0 F1). Cost per 1,000 pages: $1.31 vs $20. Median time per resume: 138 s vs 16 s.
Qwen 3.5 9B wins on 92 of 299 resumes, Reducto Extract on 200, 7 tied.
76.03
Qwen 3.5 9B
A · Vision LLM
81.69
Reducto Extract
B · Document API
Reducto Extract is ahead by 5.66 points on these 299 resumes.
- Many entries 82A 73.9 · B 79.4−5.5
- Long bullet lists 100A 73.2 · B 80.2−7.0
- Split across pages 84A 73.4 · B 79.7−6.3
- Big skills list 59A 76.3 · B 83.2−6.9
- Custom sections 104A 73.0 · B 78.2−5.2
- Combined headings 37A 72.2 · B 80.2−8.0
- Promotions 88A 74.8 · B 82.8−8.1
- Partial dates 138A 75.6 · B 80.0−4.4
- Overlapping jobs 69A 72.2 · B 80.4−8.2
- Accented text 13A 83.7 · B 87.8−4.0
Side by side
| Qwen 3.5 9B | Reducto Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | Alibaba | Reducto |
| Rank | 15 of 18 | 12 of 18 |
| F1 | 76.0 | 81.7 |
| Precision | 78.9 | 83.7 |
| Recall | 80.3 | 84.0 |
| Cost per 1,000 pages | $1.31 | $20 |
| Median time per resume | 138 s | 16 s |
| Resumes won | 92 | 200 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Qwen 3.5 9B | Reducto Extract | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 64.5 | 89.9 | −25.4 |
| Rotated & warped pages (distractors) | 21 | 66.5 | 89.2 | −22.8 |
| Hidden text & prompt injections (distractors) | 14 | 70.2 | 87.2 | −17.0 |
| Typos kept on purpose (distractors) | 37 | 72.2 | 86.2 | −14.0 |
| Two-column sidebar (layout) | 54 | 69.7 | 81.6 | −11.9 |
| Handwritten (reading the page) | 9 | 50.6 | 39.4 | +11.2 |
| Image only (reading the page) | 28 | 61.2 | 72.0 | −10.8 |
| Sidebar or grid (reading the page) | 82 | 73.5 | 82.1 | −8.6 |
| Overlapping jobs (extraction challenges) | 69 | 72.2 | 80.4 | −8.2 |
| Promotions (extraction challenges) | 88 | 74.8 | 82.8 | −8.1 |
| Combined headings (extraction challenges) | 37 | 72.2 | 80.2 | −8.0 |
| Busy page (noise) | 18 | 67.6 | 75.4 | −7.9 |
| Section | Resumes | Qwen 3.5 9B | Reducto Extract | Gap |
|---|---|---|---|---|
| Contact details | 299 | 92.6 | 93.5 | −0.9 |
| Experience | 299 | 77.2 | 83.9 | −6.7 |
| Education | 296 | 80.8 | 82.3 | −1.6 |
| Summary | 290 | 77.9 | 81.7 | −3.7 |
| Certifications | 246 | 74.7 | 81.2 | −6.5 |
| Awards | 127 | 55.2 | 73.2 | −18.0 |
| Skills | 293 | 83.2 | 93.0 | −9.8 |
| Languages | 172 | 80.0 | 84.3 | −4.3 |
| Custom sections | 214 | 36.4 | 44.4 | −8.1 |
| Interests | 68 | 84.3 | 92.8 | −8.5 |
| Volunteering | 80 | 80.2 | 82.7 | −2.5 |
| Profiles | 38 | 51.3 | 56.9 | −5.5 |
| Projects | 79 | 75.5 | 85.4 | −9.9 |
| Publications | 53 | 76.3 | 76.0 | +0.3 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Qwen 3.5 9B | Reducto Extract | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 65.0 | 89.3 | −24.3 |
| Senior Manufacturing Engineer: Third-person prose, no bullets | 71.4 | 92.4 | −21.0 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 54.9 | 74.6 | −19.7 |
| Lead Respiratory Therapist (Adult ICU): Long resume, 34 entries | 69.4 | 88.6 | −19.2 |
Which to pick
Reducto Extract is more accurate. Qwen 3.5 9B costs 93% less for 5.7 fewer points.
Qwen 3.5 9B does better on handwritten, table grid and content as images. Reducto 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 Deep 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 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 35B
- 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