GPT-5.4 Nano vs Qwen 3.5 9B: which is better at resume extraction?
Qwen 3.5 9B leads GPT-5.4 Nano by 14.2 points (76.0 vs 61.9 F1). Cost per 1,000 pages: $2.76 vs $1.31. Median time per resume: 20 s vs 138 s.
GPT-5.4 Nano wins on 68 of 299 resumes, Qwen 3.5 9B on 229, 2 tied.
61.92
GPT-5.4 Nano
A · Vision LLM
76.03
Qwen 3.5 9B
B · Vision LLM
Qwen 3.5 9B is ahead by 14.11 points on these 299 resumes.
- Many entries 82A 59.9 · B 73.9−14.0
- Long bullet lists 100A 61.2 · B 73.2−12.0
- Split across pages 84A 61.9 · B 73.4−11.5
- Big skills list 59A 65.3 · B 76.3−11.1
- Custom sections 104A 59.6 · B 73.0−13.4
- Combined headings 37A 64.6 · B 72.2−7.6
- Promotions 88A 58.7 · B 74.8−16.1
- Partial dates 138A 62.6 · B 75.6−13.0
- Overlapping jobs 69A 58.6 · B 72.2−13.5
- Accented text 13A 55.9 · B 83.7−27.9
Side by side
| GPT-5.4 Nano | Qwen 3.5 9B | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | OpenAI | Alibaba |
| Rank | 17 of 18 | 15 of 18 |
| F1 | 61.9 | 76.0 |
| Precision | 70.1 | 78.9 |
| Recall | 66.3 | 80.3 |
| Cost per 1,000 pages | $2.76 | $1.31 |
| Median time per resume | 20 s | 138 s |
| Resumes won | 68 | 229 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.4 Nano | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 6.3 | 64.5 | −58.2 |
| Rotated & warped pages (distractors) | 21 | 11.7 | 66.5 | −54.8 |
| Hidden text & prompt injections (distractors) | 14 | 22.0 | 70.2 | −48.2 |
| Image only (reading the page) | 28 | 21.0 | 61.2 | −40.2 |
| Typos kept on purpose (distractors) | 37 | 33.5 | 72.2 | −38.7 |
| Accented text (extraction challenges) | 13 | 55.9 | 83.7 | −27.9 |
| Content as images (distractors) | 8 | 61.3 | 85.9 | −24.6 |
| Two-column sidebar (layout) | 54 | 47.4 | 69.7 | −22.3 |
| Table grid (layout) | 8 | 74.4 | 93.3 | −18.9 |
| Expert-built (Canva / LaTeX) (source) | 32 | 60.3 | 79.1 | −18.8 |
| Sidebar or grid (reading the page) | 82 | 54.9 | 73.5 | −18.6 |
| Distractor layouts (source) | 18 | 62.2 | 80.4 | −18.1 |
| Section | Resumes | GPT-5.4 Nano | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Contact details | 299 | 81.2 | 92.6 | −11.3 |
| Experience | 299 | 63.6 | 77.2 | −13.6 |
| Education | 296 | 62.3 | 80.8 | −18.5 |
| Summary | 289 | 72.0 | 77.9 | −6.0 |
| Certifications | 243 | 53.8 | 74.7 | −20.9 |
| Awards | 101 | 45.4 | 55.2 | −9.8 |
| Skills | 290 | 74.7 | 83.2 | −8.5 |
| Languages | 170 | 69.0 | 80.0 | −11.0 |
| Custom sections | 230 | 26.4 | 36.4 | −10.0 |
| Interests | 66 | 70.0 | 84.3 | −14.3 |
| Volunteering | 80 | 59.9 | 80.2 | −20.3 |
| Profiles | 65 | 22.6 | 51.3 | −28.8 |
| Projects | 80 | 48.8 | 75.5 | −26.7 |
| Publications | 51 | 30.7 | 76.3 | −45.6 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.4 Nano | Qwen 3.5 9B | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 1.7 | 65.0 | −63.4 |
| Partner: Consulting CV, six pages | 27.8 | 77.9 | −50.1 |
| Head of Digital Marketing: Canva design with a photo | 39.3 | 85.2 | −45.9 |
| Quality Systems Lead: Photo of a printout | 46.0 | 79.4 | −33.3 |
Which to pick
Qwen 3.5 9B is more accurate. GPT-5.4 Nano is the faster of the two.
GPT-5.4 Nano does better on handwritten. Qwen 3.5 9B 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 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 GLM 5.3 Flash
Qwen 3.5 9B against every other model
- Qwen 3.5 9B vs LlamaParse Extract Agentic Plus
- Qwen 3.5 9B vs LlamaParse Extract Agentic
- Qwen 3.5 9B vs LlamaParse Extract Cost-Effective
- Qwen 3.5 9B vs Reducto Deep Extract
- Qwen 3.5 9B vs Reducto Extract
- Qwen 3.5 9B vs Extend Max Context
- Qwen 3.5 9B vs Extend Extract
- Qwen 3.5 9B vs GPT-5.6
- Qwen 3.5 9B vs GPT-5.5
- Qwen 3.5 9B vs Claude Opus 4.8
- Qwen 3.5 9B vs Gemini 3.5 Flash
- Qwen 3.5 9B vs Gemma 4 26B
- Qwen 3.5 9B vs Qwen 3.8 Flash
- Qwen 3.5 9B vs Qwen 3.8 27B
- Qwen 3.5 9B vs Qwen 3.5 35B
- Qwen 3.5 9B 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