GPT-5.5 vs Qwen 3.5 9B: which is better at resume extraction?
GPT-5.5 leads Qwen 3.5 9B by 7.5 points (83.5 vs 76.0 F1). Cost per 1,000 pages: $87 vs $1.31. Median time per resume: 48 s vs 138 s.
GPT-5.5 wins on 220 of 299 resumes, Qwen 3.5 9B on 71, 8 tied.
83.52
GPT-5.5
A · Vision LLM
76.03
Qwen 3.5 9B
B · Vision LLM
GPT-5.5 is ahead by 7.49 points on these 299 resumes.
- Many entries 82A 83.9 · B 73.9+10.0
- Long bullet lists 100A 84.3 · B 73.2+11.2
- Split across pages 84A 85.1 · B 73.4+11.7
- Big skills list 59A 85.6 · B 76.3+9.3
- Custom sections 104A 80.9 · B 73.0+7.8
- Combined headings 37A 83.4 · B 72.2+11.2
- Promotions 88A 84.0 · B 74.8+9.2
- Partial dates 138A 84.0 · B 75.6+8.5
- Overlapping jobs 69A 82.1 · B 72.2+9.9
- Accented text 13A 83.9 · B 83.7+0.1
Side by side
| GPT-5.5 | Qwen 3.5 9B | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | OpenAI | Alibaba |
| Rank | 11 of 18 | 15 of 18 |
| F1 | 83.5 | 76.0 |
| Precision | 84.9 | 78.9 |
| Recall | 86.0 | 80.3 |
| Cost per 1,000 pages | $87 | $1.31 |
| Median time per resume | 48 s | 138 s |
| Resumes won | 220 | 71 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.5 | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Busy page (noise) | 18 | 82.5 | 67.6 | +14.9 |
| Split across pages (extraction challenges) | 84 | 85.1 | 73.4 | +11.7 |
| Combined headings (extraction challenges) | 37 | 83.4 | 72.2 | +11.2 |
| Long bullet lists (extraction challenges) | 100 | 84.3 | 73.2 | +11.2 |
| References (noise) | 55 | 88.5 | 77.6 | +10.9 |
| Repeated header (noise) | 67 | 86.7 | 76.4 | +10.3 |
| Many entries (extraction challenges) | 82 | 83.9 | 73.9 | +10.0 |
| Overlapping jobs (extraction challenges) | 69 | 82.1 | 72.2 | +9.9 |
| Everyday resumes (source) | 211 | 86.7 | 77.2 | +9.5 |
| Big skills list (extraction challenges) | 59 | 85.6 | 76.3 | +9.3 |
| Long (length) | 61 | 77.3 | 68.0 | +9.3 |
| Two-column (layout) | 23 | 88.3 | 79.1 | +9.2 |
| Section | Resumes | GPT-5.5 | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Contact details | 299 | 93.5 | 92.6 | +0.9 |
| Experience | 299 | 87.4 | 77.2 | +10.2 |
| Education | 296 | 88.7 | 80.8 | +8.0 |
| Summary | 290 | 81.7 | 77.9 | +3.8 |
| Certifications | 253 | 77.3 | 74.7 | +2.6 |
| Awards | 97 | 75.5 | 55.2 | +20.3 |
| Skills | 286 | 91.5 | 83.2 | +8.2 |
| Languages | 168 | 85.7 | 80.0 | +5.7 |
| Custom sections | 209 | 49.8 | 36.4 | +13.4 |
| Interests | 64 | 92.4 | 84.3 | +8.1 |
| Volunteering | 77 | 85.0 | 80.2 | +4.8 |
| Profiles | 35 | 67.6 | 51.3 | +16.3 |
| Projects | 78 | 87.4 | 75.5 | +11.9 |
| Publications | 51 | 82.5 | 76.3 | +6.2 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.5 | Qwen 3.5 9B | Gap |
|---|---|---|---|
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 79.9 | 54.9 | +24.9 |
| Senior Controls Engineer: Five custom sections | 87.9 | 65.2 | +22.7 |
| Senior Game Designer: Game designer's Canva resume | 75.1 | 55.1 | +20.0 |
| Lead Respiratory Therapist (Adult ICU): Long resume, 34 entries | 88.7 | 69.4 | +19.3 |
Which to pick
GPT-5.5 is more accurate. Qwen 3.5 9B costs 98% less for 7.5 fewer points.
GPT-5.5 does better on busy page, split across pages and combined headings. Qwen 3.5 9B does better on image only, scanned & rotated and rotated & warped pages.
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 GPT-5.4 Nano
- 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 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-5.4 Nano
- 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