Qwen 3.8 Flash vs Reducto Deep Extract: which is better at resume extraction?
Reducto Deep Extract leads Qwen 3.8 Flash by 1.5 points (85.6 vs 84.1 F1). Cost per 1,000 pages: $2.98 vs $40. Median time per resume: 122 s vs 65 s.
Qwen 3.8 Flash wins on 94 of 298 resumes, Reducto Deep Extract on 158, 46 tied.
84.08
Qwen 3.8 Flash
A · Vision LLM
85.52
Reducto Deep Extract
B · Document API
Reducto Deep Extract is ahead by 1.44 points on these 298 resumes.
- Many entries 83A 82.1 · B 84.3−2.3
- Long bullet lists 101A 82.1 · B 84.5−2.4
- Split across pages 85A 82.6 · B 84.1−1.5
- Big skills list 60A 83.5 · B 85.8−2.3
- Custom sections 105A 80.8 · B 82.6−1.7
- Combined headings 37A 82.6 · B 82.7−0.1
- Promotions 86A 83.8 · B 85.9−2.1
- Partial dates 138A 83.3 · B 85.2−1.9
- Overlapping jobs 68A 81.4 · B 85.8−4.4
- Accented text 13A 86.9 · B 85.5+1.4
Side by side
| Qwen 3.8 Flash | Reducto Deep Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | Alibaba | Reducto |
| Rank | 8 of 18 | 2 of 18 |
| F1 | 84.1 | 85.6 |
| Precision | 85.4 | 87.5 |
| Recall | 86.2 | 87.3 |
| Cost per 1,000 pages | $2.98 | $40 |
| Median time per resume | 122 s | 65 s |
| Resumes won | 94 | 158 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Qwen 3.8 Flash | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Resume-builder templates (source) | 10 | 84.0 | 77.6 | +6.5 |
| References (noise) | 55 | 85.4 | 90.2 | −4.8 |
| Overlapping jobs (extraction challenges) | 68 | 81.4 | 85.8 | −4.4 |
| Handwritten (reading the page) | 9 | 53.5 | 49.4 | +4.1 |
| Busy page (noise) | 18 | 79.8 | 83.6 | −3.8 |
| Scanned & rotated (source) | 17 | 86.3 | 90.1 | −3.7 |
| Rotated & warped pages (distractors) | 19 | 86.0 | 89.1 | −3.1 |
| Long (length) | 62 | 75.0 | 77.5 | −2.5 |
| Long bullet lists (extraction challenges) | 101 | 82.1 | 84.5 | −2.4 |
| Big skills list (extraction challenges) | 60 | 83.5 | 85.8 | −2.3 |
| Table grid (layout) | 8 | 95.5 | 93.2 | +2.3 |
| Many entries (extraction challenges) | 83 | 82.1 | 84.3 | −2.3 |
| Section | Resumes | Qwen 3.8 Flash | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Contact details | 298 | 93.6 | 94.2 | −0.6 |
| Experience | 298 | 88.0 | 90.6 | −2.6 |
| Education | 295 | 90.1 | 91.9 | −1.8 |
| Summary | 288 | 81.3 | 85.1 | −3.8 |
| Certifications | 248 | 82.2 | 81.3 | +0.9 |
| Awards | 94 | 75.5 | 79.0 | −3.4 |
| Skills | 285 | 90.0 | 94.0 | −4.0 |
| Languages | 167 | 84.6 | 81.5 | +3.1 |
| Custom sections | 210 | 53.9 | 51.5 | +2.4 |
| Interests | 63 | 91.1 | 93.7 | −2.5 |
| Volunteering | 78 | 83.9 | 89.4 | −5.5 |
| Profiles | 35 | 73.3 | 69.6 | +3.7 |
| Projects | 79 | 83.7 | 88.1 | −4.4 |
| Publications | 51 | 81.8 | 79.3 | +2.5 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Qwen 3.8 Flash | Reducto Deep Extract | Gap |
|---|---|---|---|
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 83.8 | 66.6 | +17.1 |
| Creative Director: Accented text in a styled CV | 76.8 | 61.2 | +15.6 |
| Senior Game Designer: Game designer's Canva resume | 67.7 | 52.9 | +14.8 |
| Senior Manufacturing Engineer: Third-person prose, no bullets | 79.6 | 93.9 | −14.3 |
Which to pick
Reducto Deep Extract is more accurate. Qwen 3.8 Flash costs 93% less for 1.5 fewer points.
Qwen 3.8 Flash does better on resume-builder templates, handwritten and table grid. Reducto Deep Extract does better on references, overlapping jobs and busy page.
Qwen 3.8 Flash against every other model
- Qwen 3.8 Flash vs LlamaParse Extract Agentic Plus
- Qwen 3.8 Flash vs LlamaParse Extract Agentic
- Qwen 3.8 Flash vs LlamaParse Extract Cost-Effective
- Qwen 3.8 Flash vs Reducto Extract
- Qwen 3.8 Flash vs Extend Max Context
- Qwen 3.8 Flash vs Extend Extract
- Qwen 3.8 Flash vs GPT-5.6
- Qwen 3.8 Flash vs GPT-5.5
- Qwen 3.8 Flash vs GPT-5.4 Nano
- Qwen 3.8 Flash vs Claude Opus 4.8
- Qwen 3.8 Flash vs Gemini 3.5 Flash
- Qwen 3.8 Flash vs Gemma 4 26B
- Qwen 3.8 Flash vs Qwen 3.8 27B
- Qwen 3.8 Flash vs Qwen 3.5 35B
- Qwen 3.8 Flash vs Qwen 3.5 9B
- Qwen 3.8 Flash 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 27B
- Reducto Deep Extract vs Qwen 3.5 35B
- 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