GPT-5.6 vs Reducto Deep Extract: which is better at resume extraction?
Reducto Deep Extract leads GPT-5.6 by 0.8 points (85.6 vs 84.7 F1). Cost per 1,000 pages: $74 vs $40. Median time per resume: 38 s vs 65 s.
GPT-5.6 wins on 101 of 300 resumes, Reducto Deep Extract on 119, 80 tied.
84.75
GPT-5.6
A · Vision LLM
85.55
Reducto Deep Extract
B · Document API
Reducto Deep Extract is ahead by 0.80 points on these 300 resumes.
- Many entries 83A 84.5 · B 84.3+0.1
- Long bullet lists 101A 84.9 · B 84.5+0.4
- Split across pages 85A 84.9 · B 84.1+0.7
- Big skills list 60A 85.2 · B 85.8−0.6
- Custom sections 105A 82.2 · B 82.6−0.4
- Combined headings 37A 84.1 · B 82.7+1.3
- Promotions 88A 85.0 · B 86.0−1.0
- Partial dates 138A 85.7 · B 85.2+0.5
- Overlapping jobs 69A 83.2 · B 85.9−2.7
- Accented text 13A 86.5 · B 85.5+1.1
Side by side
| GPT-5.6 | Reducto Deep Extract | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | OpenAI | Reducto |
| Rank | 6 of 18 | 2 of 18 |
| F1 | 84.7 | 85.6 |
| Precision | 85.9 | 87.5 |
| Recall | 87.2 | 87.3 |
| Cost per 1,000 pages | $74 | $40 |
| Median time per resume | 38 s | 65 s |
| Resumes won | 101 | 119 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.6 | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 71.6 | 90.1 | −18.5 |
| Rotated & warped pages (distractors) | 21 | 73.2 | 89.3 | −16.0 |
| Hidden text & prompt injections (distractors) | 14 | 77.5 | 90.1 | −12.5 |
| Image only (reading the page) | 28 | 65.4 | 76.4 | −11.0 |
| Typos kept on purpose (distractors) | 37 | 80.6 | 87.9 | −7.3 |
| Resume-builder templates (source) | 10 | 83.7 | 77.6 | +6.1 |
| Two-column sidebar (layout) | 54 | 78.3 | 83.8 | −5.4 |
| Content as images (distractors) | 8 | 93.0 | 88.0 | +5.0 |
| Wording traps (distractors) | 16 | 89.1 | 84.2 | +4.9 |
| Distractor layouts (source) | 18 | 90.1 | 85.6 | +4.5 |
| Handwritten (reading the page) | 9 | 53.2 | 49.4 | +3.9 |
| Sidebar or grid (reading the page) | 82 | 81.7 | 85.2 | −3.6 |
| Section | Resumes | GPT-5.6 | Reducto Deep Extract | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.1 | 94.2 | −0.1 |
| Experience | 300 | 88.4 | 90.6 | −2.2 |
| Education | 297 | 91.9 | 92.0 | −0.1 |
| Summary | 290 | 83.4 | 85.2 | −1.7 |
| Certifications | 255 | 77.9 | 81.4 | −3.5 |
| Awards | 95 | 81.2 | 79.4 | +1.8 |
| Skills | 287 | 93.2 | 93.9 | −0.7 |
| Languages | 168 | 85.9 | 81.8 | +4.1 |
| Custom sections | 212 | 51.2 | 51.3 | −0.1 |
| Interests | 64 | 91.4 | 93.8 | −2.4 |
| Volunteering | 77 | 85.7 | 89.5 | −3.9 |
| Profiles | 37 | 69.4 | 69.6 | −0.2 |
| Projects | 80 | 88.2 | 88.1 | +0.1 |
| Publications | 51 | 77.8 | 79.3 | −1.6 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.6 | Reducto Deep Extract | Gap |
|---|---|---|---|
| Creative Director: Accented text in a styled CV | 90.8 | 61.2 | +29.6 |
| Senior Game Designer: Game designer's Canva resume | 75.9 | 52.9 | +23.0 |
| Deputy Head of Mission: Rotated scan with hidden identity text | 76.2 | 89.2 | −13.0 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 72.8 | 84.9 | −12.1 |
Which to pick
Reducto Deep Extract is more accurate. GPT-5.6 is the faster of the two.
GPT-5.6 does better on resume-builder templates, content as images and wording traps. Reducto Deep Extract does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
GPT-5.6 against every other model
- GPT-5.6 vs LlamaParse Extract Agentic Plus
- GPT-5.6 vs LlamaParse Extract Agentic
- GPT-5.6 vs LlamaParse Extract Cost-Effective
- GPT-5.6 vs Reducto Extract
- GPT-5.6 vs Extend Max Context
- GPT-5.6 vs Extend Extract
- GPT-5.6 vs GPT-5.5
- GPT-5.6 vs GPT-5.4 Nano
- GPT-5.6 vs Claude Opus 4.8
- GPT-5.6 vs Gemini 3.5 Flash
- GPT-5.6 vs Gemma 4 26B
- GPT-5.6 vs Qwen 3.8 Flash
- GPT-5.6 vs Qwen 3.8 27B
- GPT-5.6 vs Qwen 3.5 35B
- GPT-5.6 vs Qwen 3.5 9B
- GPT-5.6 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-5.5
- 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