Qwen 3.8 27B vs Reducto Extract: which is better at resume extraction?
Qwen 3.8 27B leads Reducto Extract by 2.1 points (83.8 vs 81.7 F1). Cost per 1,000 pages: $9.59 vs $20. Median time per resume: 36 s vs 16 s.
Qwen 3.8 27B wins on 161 of 300 resumes, Reducto Extract on 116, 23 tied.
83.77
Qwen 3.8 27B
A · Vision LLM
81.70
Reducto Extract
B · Document API
Qwen 3.8 27B is ahead by 2.07 points on these 300 resumes.
- Many entries 83A 81.6 · B 79.5+2.2
- Long bullet lists 101A 80.8 · B 80.2+0.6
- Split across pages 85A 81.8 · B 79.7+2.1
- Big skills list 60A 82.9 · B 83.2−0.3
- Custom sections 105A 81.0 · B 78.2+2.7
- Combined headings 37A 83.7 · B 80.2+3.5
- Promotions 88A 83.2 · B 82.8+0.4
- Partial dates 138A 83.6 · B 80.0+3.6
- Overlapping jobs 69A 82.4 · B 80.4+2.0
- Accented text 13A 84.9 · B 87.8−2.8
Side by side
| Qwen 3.8 27B | Reducto Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | Alibaba | Reducto |
| Rank | 9 of 18 | 12 of 18 |
| F1 | 83.8 | 81.7 |
| Precision | 85.4 | 83.7 |
| Recall | 85.5 | 84.0 |
| Cost per 1,000 pages | $9.59 | $20 |
| Median time per resume | 36 s | 16 s |
| Resumes won | 161 | 116 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Qwen 3.8 27B | Reducto Extract | Gap |
|---|---|---|---|---|
| Handwritten (reading the page) | 9 | 51.6 | 39.4 | +12.2 |
| Scanned & rotated (source) | 19 | 78.4 | 89.9 | −11.5 |
| Rotated & warped pages (distractors) | 21 | 78.7 | 89.2 | −10.5 |
| Wording traps (distractors) | 16 | 87.6 | 81.4 | +6.2 |
| Three-column (layout) | 20 | 85.5 | 79.9 | +5.6 |
| Distractor layouts (source) | 18 | 87.6 | 82.3 | +5.4 |
| Table grid (layout) | 8 | 95.7 | 90.8 | +5.0 |
| Resume-builder templates (source) | 10 | 86.7 | 81.8 | +4.9 |
| Busy page (noise) | 18 | 80.4 | 75.4 | +4.9 |
| Hidden text & prompt injections (distractors) | 14 | 82.4 | 87.2 | −4.8 |
| Two-column (layout) | 23 | 87.9 | 83.2 | +4.7 |
| Content as images (distractors) | 8 | 89.5 | 84.9 | +4.6 |
| Section | Resumes | Qwen 3.8 27B | Reducto Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 93.2 | 93.4 | −0.3 |
| Experience | 300 | 86.2 | 84.0 | +2.2 |
| Education | 297 | 87.2 | 82.3 | +4.8 |
| Summary | 290 | 81.7 | 81.7 | +0.0 |
| Certifications | 244 | 82.7 | 81.3 | +1.4 |
| Awards | 97 | 78.4 | 73.5 | +5.0 |
| Skills | 284 | 92.7 | 93.0 | −0.3 |
| Languages | 168 | 85.4 | 84.3 | +1.0 |
| Custom sections | 216 | 51.2 | 44.4 | +6.8 |
| Interests | 63 | 94.6 | 92.8 | +1.8 |
| Volunteering | 79 | 84.7 | 82.7 | +2.0 |
| Profiles | 34 | 72.5 | 58.1 | +14.5 |
| Projects | 78 | 85.5 | 84.6 | +0.9 |
| Publications | 51 | 77.2 | 76.0 | +1.2 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Qwen 3.8 27B | Reducto Extract | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 65.6 | 89.3 | −23.8 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 79.1 | 63.8 | +15.3 |
| Head of Events & Public Space Operations: Table grid with emoji bullets | 88.1 | 72.9 | +15.2 |
| Postdoctoral Researcher: Academic CV, seven pages | 87.0 | 71.8 | +15.2 |
Which to pick
Qwen 3.8 27B is more accurate. Reducto Extract is the faster of the two.
Qwen 3.8 27B does better on handwritten, wording traps and three-column. Reducto Extract does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
Qwen 3.8 27B against every other model
- Qwen 3.8 27B vs LlamaParse Extract Agentic Plus
- 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 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
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 3.5 35B
- 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