Reducto Deep Extract vs Reducto Extract: which is better at resume extraction?
Reducto Deep Extract leads Reducto Extract by 3.9 points (85.6 vs 81.7 F1). Cost per 1,000 pages: $40 vs $20. Median time per resume: 65 s vs 16 s.
Reducto Deep Extract wins on 187 of 300 resumes, Reducto Extract on 78, 35 tied.
85.55
Reducto Deep Extract
A · Document API
81.70
Reducto Extract
B · Document API
Reducto Deep Extract is ahead by 3.86 points on these 300 resumes.
- Many entries 83A 84.3 · B 79.5+4.9
- Long bullet lists 101A 84.5 · B 80.2+4.3
- Split across pages 85A 84.1 · B 79.7+4.4
- Big skills list 60A 85.8 · B 83.2+2.6
- Custom sections 105A 82.6 · B 78.2+4.3
- Combined headings 37A 82.7 · B 80.2+2.5
- Promotions 88A 86.0 · B 82.8+3.1
- Partial dates 138A 85.2 · B 80.0+5.2
- Overlapping jobs 69A 85.9 · B 80.4+5.5
- Accented text 13A 85.5 · B 87.8−2.3
Side by side
| Reducto Deep Extract | Reducto Extract | |
|---|---|---|
| Type | Document API | Document API |
| Maker | Reducto | Reducto |
| Rank | 2 of 18 | 12 of 18 |
| F1 | 85.6 | 81.7 |
| Precision | 87.5 | 83.7 |
| Recall | 87.3 | 84.0 |
| Cost per 1,000 pages | $40 | $20 |
| Median time per resume | 65 s | 16 s |
| Resumes won | 187 | 78 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Reducto Deep Extract | Reducto Extract | Gap |
|---|---|---|---|---|
| Handwritten (reading the page) | 9 | 49.4 | 39.4 | +10.0 |
| Busy page (noise) | 18 | 83.6 | 75.4 | +8.2 |
| Three-column (layout) | 20 | 86.0 | 79.9 | +6.1 |
| References (noise) | 55 | 90.2 | 84.4 | +5.8 |
| Long (length) | 62 | 77.5 | 71.9 | +5.6 |
| Overlapping jobs (extraction challenges) | 69 | 85.9 | 80.4 | +5.5 |
| Partial dates (extraction challenges) | 138 | 85.2 | 80.0 | +5.2 |
| Many entries (extraction challenges) | 83 | 84.3 | 79.5 | +4.9 |
| Expert-built (Canva / LaTeX) (source) | 32 | 84.6 | 80.0 | +4.5 |
| Photo (reading the page) | 45 | 86.4 | 81.9 | +4.5 |
| Split across pages (extraction challenges) | 85 | 84.1 | 79.7 | +4.4 |
| Image only (reading the page) | 28 | 76.4 | 72.0 | +4.4 |
| Section | Resumes | Reducto Deep Extract | Reducto Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.2 | 93.4 | +0.8 |
| Experience | 300 | 90.6 | 84.0 | +6.6 |
| Education | 297 | 92.0 | 82.3 | +9.7 |
| Summary | 290 | 85.2 | 81.7 | +3.4 |
| Certifications | 252 | 81.4 | 81.3 | +0.1 |
| Awards | 94 | 79.4 | 73.5 | +5.9 |
| Skills | 285 | 93.9 | 93.0 | +0.9 |
| Languages | 167 | 81.8 | 84.3 | −2.6 |
| Custom sections | 212 | 51.3 | 44.4 | +6.9 |
| Interests | 64 | 93.8 | 92.8 | +0.9 |
| Volunteering | 77 | 89.5 | 82.7 | +6.9 |
| Profiles | 34 | 69.6 | 58.1 | +11.5 |
| Projects | 77 | 88.1 | 84.6 | +3.4 |
| Publications | 50 | 79.3 | 76.0 | +3.3 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Reducto Deep Extract | Reducto Extract | Gap |
|---|---|---|---|
| Senior Data Scientist (Lead): Fifty skills, seven pages | 84.9 | 63.8 | +21.1 |
| Senior Full-Stack Engineer: LaTeX CV with a running header | 77.7 | 62.8 | +15.0 |
| senior Consultant - package Implementation: Handwritten resume | 54.8 | 40.0 | +14.8 |
| Creative Director: Accented text in a styled CV | 61.2 | 75.4 | −14.2 |
Which to pick
Reducto Deep Extract is more accurate. Reducto Extract costs 50% less for 3.9 fewer points.
Reducto Deep Extract does better on handwritten, busy page and three-column. Reducto Extract does better on resume-builder templates and accented text.
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 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 Qwen 3.5 9B
- Reducto Deep Extract 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 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 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
- Gemma 4 26B vs Qwen 3.8 27B
- Document APIs vs vision LLMs