GPT-5.6 vs Qwen 3.5 35B: which is better at resume extraction?
GPT-5.6 leads Qwen 3.5 35B by 6.8 points (84.7 vs 77.9 F1). Cost per 1,000 pages: $74 vs $3.91. Median time per resume: 38 s vs 78 s.
GPT-5.6 wins on 212 of 300 resumes, Qwen 3.5 35B on 81, 7 tied.
84.75
GPT-5.6
A · Vision LLM
77.95
Qwen 3.5 35B
B · Vision LLM
GPT-5.6 is ahead by 6.80 points on these 300 resumes.
- Many entries 83A 84.5 · B 78.9+5.5
- Long bullet lists 101A 84.9 · B 76.3+8.6
- Split across pages 85A 84.9 · B 76.5+8.4
- Big skills list 60A 85.2 · B 76.6+8.5
- Custom sections 105A 82.2 · B 77.0+5.1
- Combined headings 37A 84.1 · B 74.6+9.5
- Promotions 88A 85.0 · B 76.7+8.3
- Partial dates 138A 85.7 · B 78.9+6.8
- Overlapping jobs 69A 83.2 · B 76.2+7.0
- Accented text 13A 86.5 · B 80.4+6.1
Side by side
| GPT-5.6 | Qwen 3.5 35B | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | OpenAI | Alibaba |
| Rank | 6 of 18 | 14 of 18 |
| F1 | 84.7 | 77.9 |
| Precision | 85.9 | 78.8 |
| Recall | 87.2 | 83.7 |
| Cost per 1,000 pages | $74 | $3.91 |
| Median time per resume | 38 s | 78 s |
| Resumes won | 212 | 81 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.6 | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Busy page (noise) | 18 | 84.0 | 71.8 | +12.2 |
| Two-column (layout) | 23 | 89.0 | 77.4 | +11.6 |
| Three-column (layout) | 20 | 85.6 | 75.6 | +10.0 |
| Combined headings (extraction challenges) | 37 | 84.1 | 74.6 | +9.5 |
| Everyday resumes (source) | 212 | 86.8 | 77.7 | +9.1 |
| Long bullet lists (extraction challenges) | 101 | 84.9 | 76.3 | +8.6 |
| Big skills list (extraction challenges) | 60 | 85.2 | 76.6 | +8.5 |
| Split across pages (extraction challenges) | 85 | 84.9 | 76.5 | +8.4 |
| Promotions (extraction challenges) | 88 | 85.0 | 76.7 | +8.3 |
| Repeated header (noise) | 67 | 86.8 | 78.6 | +8.3 |
| Short (length) | 148 | 87.2 | 79.8 | +7.4 |
| Overlapping jobs (extraction challenges) | 69 | 83.2 | 76.2 | +7.0 |
| Section | Resumes | GPT-5.6 | Qwen 3.5 35B | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.1 | 92.1 | +2.0 |
| Experience | 300 | 88.4 | 79.3 | +9.1 |
| Education | 297 | 91.9 | 81.8 | +10.1 |
| Summary | 290 | 83.4 | 80.4 | +3.0 |
| Certifications | 255 | 77.9 | 79.1 | −1.2 |
| Awards | 95 | 81.2 | 61.9 | +19.3 |
| Skills | 287 | 93.2 | 87.8 | +5.4 |
| Languages | 168 | 85.9 | 79.4 | +6.5 |
| Custom sections | 212 | 51.2 | 40.2 | +11.0 |
| Interests | 64 | 91.4 | 89.7 | +1.6 |
| Volunteering | 77 | 85.7 | 83.1 | +2.5 |
| Profiles | 37 | 69.4 | 65.8 | +3.6 |
| Projects | 80 | 88.2 | 76.7 | +11.4 |
| Publications | 51 | 77.8 | 75.0 | +2.8 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.6 | Qwen 3.5 35B | Gap |
|---|---|---|---|
| Senior Customer Service Representative: Busy Canva page | 83.1 | 70.7 | +12.3 |
| Graphic Designer: Graphic designer's Canva CV | 72.1 | 84.4 | −12.3 |
| senior Consultant - package Implementation: Handwritten resume | 47.2 | 59.2 | −12.0 |
| Lead Solutions Architect: Indian format with CGPA | 83.8 | 72.3 | +11.5 |
Which to pick
GPT-5.6 is more accurate. Qwen 3.5 35B costs 95% less for 6.8 fewer points.
GPT-5.6 does better on busy page, two-column and three-column. Qwen 3.5 35B does better on image only, scanned & rotated and rotated & warped pages.
GPT-5.6 against every other model
- GPT-5.6 vs LlamaParse Extract Agentic Plus
- GPT-5.6 vs LlamaParse Extract Agentic
- GPT-5.6 vs LlamaParse Extract Cost-Effective
- GPT-5.6 vs Reducto Deep Extract
- GPT-5.6 vs Reducto Extract
- GPT-5.6 vs Extend Max Context
- GPT-5.6 vs Extend Extract
- GPT-5.6 vs GPT-5.5
- GPT-5.6 vs GPT-5.4 Nano
- GPT-5.6 vs Claude Opus 4.8
- GPT-5.6 vs Gemini 3.5 Flash
- GPT-5.6 vs Gemma 4 26B
- GPT-5.6 vs Qwen 3.8 Flash
- GPT-5.6 vs Qwen 3.8 27B
- GPT-5.6 vs Qwen 3.5 9B
- GPT-5.6 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-5.5
- 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