GPT-5.5 vs Qwen 3.5 35B: which is better at resume extraction?
GPT-5.5 leads Qwen 3.5 35B by 5.6 points (83.5 vs 77.9 F1). Cost per 1,000 pages: $87 vs $3.91. Median time per resume: 48 s vs 78 s.
GPT-5.5 wins on 201 of 300 resumes, Qwen 3.5 35B on 93, 6 tied.
83.50
GPT-5.5
A · Vision LLM
77.95
Qwen 3.5 35B
B · Vision LLM
GPT-5.5 is ahead by 5.55 points on these 300 resumes.
- Many entries 83A 83.8 · B 78.9+4.9
- Long bullet lists 101A 84.3 · B 76.3+8.0
- Split across pages 85A 85.0 · B 76.5+8.5
- Big skills list 60A 85.5 · B 76.6+8.9
- Custom sections 105A 80.8 · B 77.0+3.8
- Combined headings 37A 83.4 · B 74.6+8.8
- Promotions 88A 84.0 · B 76.7+7.3
- Partial dates 138A 84.0 · B 78.9+5.2
- Overlapping jobs 69A 82.1 · B 76.2+5.9
- Accented text 13A 83.9 · B 80.4+3.4
Side by side
| GPT-5.5 | Qwen 3.5 35B | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | OpenAI | Alibaba |
| Rank | 11 of 18 | 14 of 18 |
| F1 | 83.5 | 77.9 |
| Precision | 84.9 | 78.8 |
| Recall | 86.0 | 83.7 |
| Cost per 1,000 pages | $87 | $3.91 |
| Median time per resume | 48 s | 78 s |
| Resumes won | 201 | 93 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.5 | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 60.7 | 75.3 | −14.6 |
| Rotated & warped pages (distractors) | 21 | 63.4 | 76.5 | −13.2 |
| Image only (reading the page) | 28 | 57.0 | 69.7 | −12.7 |
| Two-column (layout) | 23 | 88.3 | 77.4 | +11.0 |
| Busy page (noise) | 18 | 82.5 | 71.8 | +10.7 |
| Hidden text & prompt injections (distractors) | 14 | 69.1 | 79.2 | −10.1 |
| Everyday resumes (source) | 212 | 86.6 | 77.7 | +9.0 |
| Big skills list (extraction challenges) | 60 | 85.5 | 76.6 | +8.9 |
| Combined headings (extraction challenges) | 37 | 83.4 | 74.6 | +8.8 |
| Split across pages (extraction challenges) | 85 | 85.0 | 76.5 | +8.5 |
| Repeated header (noise) | 67 | 86.7 | 78.6 | +8.1 |
| Long bullet lists (extraction challenges) | 101 | 84.3 | 76.3 | +8.0 |
| Section | Resumes | GPT-5.5 | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 93.5 | 92.1 | +1.4 |
| Experience | 300 | 87.4 | 79.3 | +8.1 |
| Education | 297 | 88.7 | 81.8 | +7.0 |
| Summary | 291 | 81.8 | 80.4 | +1.4 |
| Certifications | 254 | 77.3 | 79.1 | −1.7 |
| Awards | 98 | 75.3 | 61.9 | +13.4 |
| Skills | 287 | 91.5 | 87.8 | +3.7 |
| Languages | 168 | 85.7 | 79.4 | +6.3 |
| Custom sections | 210 | 49.7 | 40.2 | +9.5 |
| Interests | 64 | 92.4 | 89.7 | +2.7 |
| Volunteering | 77 | 85.0 | 83.1 | +1.9 |
| Profiles | 36 | 68.5 | 65.8 | +2.7 |
| Projects | 79 | 86.4 | 76.7 | +9.6 |
| Publications | 51 | 82.5 | 75.0 | +7.5 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.5 | Qwen 3.5 35B | Gap |
|---|---|---|---|
| Senior Customer Service Representative: Busy Canva page | 85.8 | 70.7 | +15.1 |
| Deputy Head of Mission: Rotated scan with hidden identity text | 64.7 | 79.6 | −15.0 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 71.2 | 84.1 | −12.9 |
| Graphic Designer: Graphic designer's Canva CV | 72.1 | 84.4 | −12.3 |
Which to pick
GPT-5.5 is more accurate. Qwen 3.5 35B costs 96% less for 5.6 fewer points.
GPT-5.5 does better on two-column, busy page and everyday resumes. Qwen 3.5 35B does better on scanned & rotated, rotated & warped pages and image only.
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 9B
- GPT-5.5 vs GLM 5.3 Flash
Qwen 3.5 35B against every other model
- Qwen 3.5 35B vs LlamaParse Extract Agentic Plus
- Qwen 3.5 35B vs LlamaParse Extract Agentic
- Qwen 3.5 35B vs LlamaParse Extract Cost-Effective
- Qwen 3.5 35B vs Reducto Deep Extract
- Qwen 3.5 35B vs Reducto Extract
- Qwen 3.5 35B vs Extend Max Context
- Qwen 3.5 35B vs Extend Extract
- Qwen 3.5 35B vs GPT-5.6
- Qwen 3.5 35B vs GPT-5.4 Nano
- Qwen 3.5 35B vs Claude Opus 4.8
- Qwen 3.5 35B vs Gemini 3.5 Flash
- Qwen 3.5 35B vs Gemma 4 26B
- Qwen 3.5 35B vs Qwen 3.8 Flash
- Qwen 3.5 35B vs Qwen 3.8 27B
- Qwen 3.5 35B vs Qwen 3.5 9B
- Qwen 3.5 35B 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