GPT-5.4 Nano vs GPT-5.5: which is better at resume extraction?
GPT-5.5 leads GPT-5.4 Nano by 21.6 points (83.5 vs 61.9 F1). Cost per 1,000 pages: $2.76 vs $87. Median time per resume: 20 s vs 48 s.
GPT-5.4 Nano wins on 28 of 300 resumes, GPT-5.5 on 269, 3 tied.
61.86
GPT-5.4 Nano
A · Vision LLM
83.50
GPT-5.5
B · Vision LLM
GPT-5.5 is ahead by 21.64 points on these 300 resumes.
- Many entries 83A 59.7 · B 83.8−24.1
- Long bullet lists 101A 61.0 · B 84.3−23.3
- Split across pages 85A 61.7 · B 85.0−23.4
- Big skills list 60A 64.9 · B 85.5−20.6
- Custom sections 105A 59.5 · B 80.8−21.3
- Combined headings 37A 64.6 · B 83.4−18.8
- Promotions 88A 58.7 · B 84.0−25.3
- Partial dates 138A 62.6 · B 84.0−21.5
- Overlapping jobs 69A 58.6 · B 82.1−23.4
- Accented text 13A 55.9 · B 83.9−28.0
Side by side
| GPT-5.4 Nano | GPT-5.5 | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | OpenAI | OpenAI |
| Rank | 17 of 18 | 11 of 18 |
| F1 | 61.9 | 83.5 |
| Precision | 70.1 | 84.9 |
| Recall | 66.3 | 86.0 |
| Cost per 1,000 pages | $2.76 | $87 |
| Median time per resume | 20 s | 48 s |
| Resumes won | 28 | 269 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.4 Nano | GPT-5.5 | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 6.3 | 60.7 | −54.4 |
| Rotated & warped pages (distractors) | 21 | 11.7 | 63.4 | −51.7 |
| Hidden text & prompt injections (distractors) | 14 | 22.0 | 69.1 | −47.1 |
| Typos kept on purpose (distractors) | 37 | 33.5 | 73.3 | −39.8 |
| Image only (reading the page) | 28 | 21.0 | 57.0 | −36.0 |
| Content as images (distractors) | 8 | 61.3 | 92.6 | −31.2 |
| Two-column sidebar (layout) | 54 | 47.4 | 77.2 | −29.8 |
| Accented text (extraction challenges) | 13 | 55.9 | 83.9 | −28.0 |
| Sidebar or grid (reading the page) | 82 | 54.9 | 80.4 | −25.6 |
| Promotions (extraction challenges) | 88 | 58.7 | 84.0 | −25.3 |
| Medium (length) | 90 | 60.2 | 84.9 | −24.7 |
| Photo (reading the page) | 45 | 59.4 | 84.0 | −24.7 |
| Section | Resumes | GPT-5.4 Nano | GPT-5.5 | Gap |
|---|---|---|---|---|
| Contact details | 300 | 81.2 | 93.5 | −12.3 |
| Experience | 300 | 63.7 | 87.4 | −23.7 |
| Education | 297 | 62.2 | 88.7 | −26.6 |
| Summary | 290 | 71.7 | 81.8 | −10.1 |
| Certifications | 244 | 53.6 | 77.3 | −23.8 |
| Awards | 102 | 44.9 | 75.3 | −30.3 |
| Skills | 291 | 74.8 | 91.5 | −16.7 |
| Languages | 170 | 69.0 | 85.7 | −16.7 |
| Custom sections | 231 | 26.3 | 49.7 | −23.4 |
| Interests | 66 | 70.0 | 92.4 | −22.4 |
| Volunteering | 80 | 59.9 | 85.0 | −25.1 |
| Profiles | 66 | 23.7 | 68.5 | −44.8 |
| Projects | 81 | 48.8 | 86.4 | −37.6 |
| Publications | 51 | 30.7 | 82.5 | −51.8 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.4 Nano | GPT-5.5 | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 1.7 | 64.7 | −63.0 |
| Partner: Consulting CV, six pages | 27.8 | 77.0 | −49.2 |
| Head of Digital Marketing: Canva design with a photo | 39.3 | 86.7 | −47.5 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 32.5 | 79.9 | −47.4 |
Which to pick
GPT-5.5 is more accurate. GPT-5.4 Nano costs 97% less for 21.6 fewer points.
GPT-5.5 does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
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 Extend Extract
- GPT-5.4 Nano vs GPT-5.6
- 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
GPT-5.5 against every other model
- GPT-5.5 vs LlamaParse Extract Agentic Plus
- GPT-5.5 vs LlamaParse Extract Agentic
- GPT-5.5 vs LlamaParse Extract Cost-Effective
- GPT-5.5 vs Reducto Deep Extract
- GPT-5.5 vs Reducto Extract
- GPT-5.5 vs Extend Max Context
- GPT-5.5 vs Extend Extract
- GPT-5.5 vs GPT-5.6
- GPT-5.5 vs Claude Opus 4.8
- GPT-5.5 vs Gemini 3.5 Flash
- GPT-5.5 vs Gemma 4 26B
- GPT-5.5 vs Qwen 3.8 Flash
- GPT-5.5 vs Qwen 3.8 27B
- GPT-5.5 vs Qwen 3.5 35B
- GPT-5.5 vs Qwen 3.5 9B
- GPT-5.5 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