Extend Extract vs GPT-5.4 Nano: which is better at resume extraction?
Extend Extract leads GPT-5.4 Nano by 19.1 points (81.0 vs 61.9 F1). Cost per 1,000 pages: $12 vs $2.76. Median time per resume: 31 s vs 20 s.
Extend Extract wins on 260 of 300 resumes, GPT-5.4 Nano on 39, 1 tied.
80.97
Extend Extract
A · Document API
61.86
GPT-5.4 Nano
B · Vision LLM
Extend Extract is ahead by 19.11 points on these 300 resumes.
- Many entries 83A 80.2 · B 59.7+20.6
- Long bullet lists 101A 79.8 · B 61.0+18.8
- Split across pages 85A 79.6 · B 61.7+17.9
- Big skills list 60A 81.4 · B 64.9+16.5
- Custom sections 105A 77.3 · B 59.5+17.8
- Combined headings 37A 78.0 · B 64.6+13.4
- Promotions 88A 81.7 · B 58.7+23.0
- Partial dates 138A 80.1 · B 62.6+17.5
- Overlapping jobs 69A 81.2 · B 58.6+22.6
- Accented text 13A 84.3 · B 55.9+28.4
Side by side
| Extend Extract | GPT-5.4 Nano | |
|---|---|---|
| Type | Document API | Vision LLM |
| Maker | Extend | OpenAI |
| Rank | 13 of 18 | 17 of 18 |
| F1 | 81.0 | 61.9 |
| Precision | 82.9 | 70.1 |
| Recall | 83.2 | 66.3 |
| Cost per 1,000 pages | $12 | $2.76 |
| Median time per resume | 31 s | 20 s |
| Resumes won | 260 | 39 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Extend Extract | GPT-5.4 Nano | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 79.5 | 6.3 | +73.2 |
| Rotated & warped pages (distractors) | 21 | 79.8 | 11.7 | +68.2 |
| Hidden text & prompt injections (distractors) | 14 | 82.4 | 22.0 | +60.4 |
| Image only (reading the page) | 28 | 70.7 | 21.0 | +49.8 |
| Typos kept on purpose (distractors) | 37 | 82.3 | 33.5 | +48.8 |
| Two-column sidebar (layout) | 54 | 78.3 | 47.4 | +30.9 |
| Accented text (extraction challenges) | 13 | 84.3 | 55.9 | +28.4 |
| Content as images (distractors) | 8 | 88.2 | 61.3 | +26.9 |
| Sidebar or grid (reading the page) | 82 | 80.0 | 54.9 | +25.1 |
| Promotions (extraction challenges) | 88 | 81.7 | 58.7 | +23.0 |
| Distractor layouts (source) | 18 | 85.2 | 62.2 | +23.0 |
| Overlapping jobs (extraction challenges) | 69 | 81.2 | 58.6 | +22.6 |
| Section | Resumes | Extend Extract | GPT-5.4 Nano | Gap |
|---|---|---|---|---|
| Contact details | 300 | 91.1 | 81.2 | +9.9 |
| Experience | 300 | 81.0 | 63.7 | +17.3 |
| Education | 297 | 90.2 | 62.2 | +28.0 |
| Summary | 290 | 80.7 | 71.7 | +9.0 |
| Certifications | 254 | 75.7 | 53.6 | +22.1 |
| Awards | 99 | 73.8 | 44.9 | +28.9 |
| Skills | 287 | 88.7 | 74.8 | +13.9 |
| Languages | 167 | 85.1 | 69.0 | +16.1 |
| Custom sections | 212 | 44.4 | 26.3 | +18.0 |
| Interests | 64 | 90.9 | 70.0 | +20.9 |
| Volunteering | 77 | 84.5 | 59.9 | +24.6 |
| Profiles | 36 | 42.6 | 23.7 | +18.9 |
| Projects | 82 | 80.2 | 48.8 | +31.4 |
| Publications | 51 | 85.1 | 30.7 | +54.4 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Extend Extract | GPT-5.4 Nano | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 82.7 | 1.7 | +81.1 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 83.0 | 32.5 | +50.5 |
| Partner: Consulting CV, six pages | 72.2 | 27.8 | +44.4 |
| Head of Digital Marketing: Canva design with a photo | 74.0 | 39.3 | +34.7 |
Which to pick
Extend Extract is more accurate. GPT-5.4 Nano costs 77% less for 19.1 fewer points.
Extend 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 Reducto Extract
- Extend Extract vs Extend Max Context
- Extend Extract vs GPT-5.6
- Extend Extract vs GPT-5.5
- 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
GPT-5.4 Nano against every other model
- GPT-5.4 Nano vs LlamaParse Extract Agentic Plus
- GPT-5.4 Nano vs LlamaParse Extract Agentic
- GPT-5.4 Nano vs LlamaParse Extract Cost-Effective
- GPT-5.4 Nano vs Reducto Deep Extract
- GPT-5.4 Nano vs Reducto Extract
- GPT-5.4 Nano vs Extend Max Context
- GPT-5.4 Nano vs GPT-5.6
- GPT-5.4 Nano vs GPT-5.5
- GPT-5.4 Nano vs Claude Opus 4.8
- GPT-5.4 Nano vs Gemini 3.5 Flash
- GPT-5.4 Nano vs Gemma 4 26B
- GPT-5.4 Nano vs Qwen 3.8 Flash
- GPT-5.4 Nano vs Qwen 3.8 27B
- GPT-5.4 Nano vs Qwen 3.5 35B
- GPT-5.4 Nano vs Qwen 3.5 9B
- GPT-5.4 Nano 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