Extend Extract vs Reducto Deep Extract: which is better at resume extraction?
Reducto Deep Extract leads Extend Extract by 4.6 points (85.6 vs 81.0 F1). Cost per 1,000 pages: $12 vs $40. Median time per resume: 31 s vs 65 s.
Extend Extract wins on 65 of 300 resumes, Reducto Deep Extract on 210, 25 tied.
80.97
Extend Extract
A · Document API
85.55
Reducto Deep Extract
B · Document API
Reducto Deep Extract is ahead by 4.58 points on these 300 resumes.
- Many entries 83A 80.2 · B 84.3−4.1
- Long bullet lists 101A 79.8 · B 84.5−4.7
- Split across pages 85A 79.6 · B 84.1−4.6
- Big skills list 60A 81.4 · B 85.8−4.4
- Custom sections 105A 77.3 · B 82.6−5.3
- Combined headings 37A 78.0 · B 82.7−4.8
- Promotions 88A 81.7 · B 86.0−4.3
- Partial dates 138A 80.1 · B 85.2−5.1
- Overlapping jobs 69A 81.2 · B 85.9−4.6
- Accented text 13A 84.3 · B 85.5−1.2
Side by side
| Extend Extract | Reducto Deep Extract | |
|---|---|---|
| Type | Document API | Document API |
| Maker | Extend | Reducto |
| Rank | 13 of 18 | 2 of 18 |
| F1 | 81.0 | 85.6 |
| Precision | 82.9 | 87.5 |
| Recall | 83.2 | 87.3 |
| Cost per 1,000 pages | $12 | $40 |
| Median time per resume | 31 s | 65 s |
| Resumes won | 65 | 210 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Extend Extract | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 79.5 | 90.1 | −10.6 |
| Rotated & warped pages (distractors) | 21 | 79.8 | 89.3 | −9.4 |
| Photo (reading the page) | 45 | 78.5 | 86.4 | −7.9 |
| Hidden text & prompt injections (distractors) | 14 | 82.4 | 90.1 | −7.6 |
| Expert-built (Canva / LaTeX) (source) | 32 | 77.1 | 84.6 | −7.5 |
| Image only (reading the page) | 28 | 70.7 | 76.4 | −5.7 |
| Two-column (layout) | 23 | 81.3 | 86.9 | −5.7 |
| Typos kept on purpose (distractors) | 37 | 82.3 | 87.9 | −5.6 |
| Three-column (layout) | 20 | 80.4 | 86.0 | −5.6 |
| Two-column sidebar (layout) | 54 | 78.3 | 83.8 | −5.4 |
| References (noise) | 55 | 84.8 | 90.2 | −5.4 |
| Busy page (noise) | 18 | 78.2 | 83.6 | −5.4 |
| Section | Resumes | Extend Extract | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 91.1 | 94.2 | −3.1 |
| Experience | 300 | 81.0 | 90.6 | −9.6 |
| Education | 297 | 90.2 | 92.0 | −1.8 |
| Summary | 290 | 80.7 | 85.2 | −4.5 |
| Certifications | 254 | 75.7 | 81.4 | −5.7 |
| Awards | 99 | 73.8 | 79.4 | −5.5 |
| Skills | 287 | 88.7 | 93.9 | −5.2 |
| Languages | 167 | 85.1 | 81.8 | +3.4 |
| Custom sections | 212 | 44.4 | 51.3 | −6.9 |
| Interests | 64 | 90.9 | 93.8 | −2.8 |
| Volunteering | 77 | 84.5 | 89.5 | −5.1 |
| Profiles | 36 | 42.6 | 69.6 | −27.0 |
| Projects | 82 | 80.2 | 88.1 | −7.9 |
| Publications | 51 | 85.1 | 79.3 | +5.8 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Extend Extract | Reducto Deep Extract | Gap |
|---|---|---|---|
| Head of Developer Experience (Internal title: Jedi Master of Analytics) : Unusual job titles | 55.1 | 83.4 | −28.3 |
| Postdoctoral Researcher: Academic CV, seven pages | 54.2 | 79.9 | −25.7 |
| Creative Director: Accented text in a styled CV | 81.6 | 61.2 | +20.4 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 83.0 | 66.6 | +16.4 |
Which to pick
Reducto Deep Extract is more accurate. Extend Extract costs 70% less for 4.6 fewer points.
Extend Extract does better on handwritten and resume-builder templates. Reducto Deep Extract does better on scanned & rotated, rotated & warped pages and photo.
Extend Extract against every other model
- Extend Extract vs LlamaParse Extract Agentic Plus
- Extend Extract vs LlamaParse Extract Agentic
- Extend Extract vs LlamaParse Extract Cost-Effective
- Extend Extract vs Reducto Extract
- Extend Extract vs Extend Max Context
- Extend Extract vs GPT-5.6
- Extend Extract vs GPT-5.5
- Extend Extract vs GPT-5.4 Nano
- Extend Extract vs Claude Opus 4.8
- Extend Extract vs Gemini 3.5 Flash
- Extend Extract vs Gemma 4 26B
- Extend Extract vs Qwen 3.8 Flash
- Extend Extract vs Qwen 3.8 27B
- Extend Extract vs Qwen 3.5 35B
- Extend Extract vs Qwen 3.5 9B
- Extend Extract 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 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
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