Extend Extract vs Reducto Extract: which is better at resume extraction?
Reducto Extract leads Extend Extract by 0.7 points (81.7 vs 81.0 F1). Cost per 1,000 pages: $12 vs $20. Median time per resume: 31 s vs 16 s.
Extend Extract wins on 133 of 300 resumes, Reducto Extract on 154, 13 tied.
80.97
Extend Extract
A · Document API
81.70
Reducto Extract
B · Document API
Reducto Extract is ahead by 0.73 points on these 300 resumes.
- Many entries 83A 80.2 · B 79.5+0.8
- Long bullet lists 101A 79.8 · B 80.2−0.4
- Split across pages 85A 79.6 · B 79.7−0.1
- Big skills list 60A 81.4 · B 83.2−1.7
- Custom sections 105A 77.3 · B 78.2−0.9
- Combined headings 37A 78.0 · B 80.2−2.3
- Promotions 88A 81.7 · B 82.8−1.1
- Partial dates 138A 80.1 · B 80.0+0.1
- Overlapping jobs 69A 81.2 · B 80.4+0.9
- Accented text 13A 84.3 · B 87.8−3.5
Side by side
| Extend Extract | Reducto Extract | |
|---|---|---|
| Type | Document API | Document API |
| Maker | Extend | Reducto |
| Rank | 13 of 18 | 12 of 18 |
| F1 | 81.0 | 81.7 |
| Precision | 82.9 | 83.7 |
| Recall | 83.2 | 84.0 |
| Cost per 1,000 pages | $12 | $20 |
| Median time per resume | 31 s | 16 s |
| Resumes won | 133 | 154 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Extend Extract | Reducto Extract | Gap |
|---|---|---|---|---|
| Handwritten (reading the page) | 9 | 52.5 | 39.4 | +13.1 |
| Scanned & rotated (source) | 19 | 79.5 | 89.9 | −10.4 |
| Rotated & warped pages (distractors) | 21 | 79.8 | 89.2 | −9.4 |
| Hidden text & prompt injections (distractors) | 14 | 82.4 | 87.2 | −4.8 |
| Typos kept on purpose (distractors) | 37 | 82.3 | 86.2 | −3.9 |
| Accented text (extraction challenges) | 13 | 84.3 | 87.8 | −3.5 |
| Photo (reading the page) | 45 | 78.5 | 81.9 | −3.4 |
| Content as images (distractors) | 8 | 88.2 | 84.9 | +3.3 |
| Two-column sidebar (layout) | 54 | 78.3 | 81.6 | −3.3 |
| Distractor layouts (source) | 18 | 85.2 | 82.3 | +2.9 |
| Expert-built (Canva / LaTeX) (source) | 32 | 77.1 | 80.0 | −2.9 |
| Busy page (noise) | 18 | 78.2 | 75.4 | +2.8 |
| Section | Resumes | Extend Extract | Reducto Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 91.1 | 93.4 | −2.4 |
| Experience | 300 | 81.0 | 84.0 | −3.0 |
| Education | 297 | 90.2 | 82.3 | +7.9 |
| Summary | 290 | 80.7 | 81.7 | −1.0 |
| Certifications | 254 | 75.7 | 81.3 | −5.6 |
| Awards | 99 | 73.8 | 73.5 | +0.4 |
| Skills | 287 | 88.7 | 93.0 | −4.3 |
| Languages | 167 | 85.1 | 84.3 | +0.8 |
| Custom sections | 212 | 44.4 | 44.4 | −0.0 |
| Interests | 64 | 90.9 | 92.8 | −1.9 |
| Volunteering | 77 | 84.5 | 82.7 | +1.8 |
| Profiles | 36 | 42.6 | 58.1 | −15.5 |
| Projects | 82 | 80.2 | 84.6 | −4.4 |
| Publications | 51 | 85.1 | 76.0 | +9.1 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Extend Extract | Reducto Extract | Gap |
|---|---|---|---|
| Head of Developer Experience (Internal title: Jedi Master of Analytics) : Unusual job titles | 55.1 | 93.5 | −38.4 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 86.3 | 63.8 | +22.5 |
| Postdoctoral Researcher: Academic CV, seven pages | 54.2 | 71.8 | −17.6 |
| senior Consultant - package Implementation: Handwritten resume | 55.4 | 40.0 | +15.4 |
Which to pick
Reducto Extract is more accurate. Extend Extract costs 40% less for 0.7 fewer points.
Extend Extract does better on handwritten, content as images and distractor layouts. Reducto Extract does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
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 Deep 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 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 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
- Reducto Deep Extract vs Reducto Extract
- Gemma 4 26B vs Qwen 3.8 27B
- Document APIs vs vision LLMs