GLM 5.3 Flash vs Qwen 3.5 9B: which is better at resume extraction?
Qwen 3.5 9B leads GLM 5.3 Flash by 16.8 points (76.0 vs 59.2 F1). Cost per 1,000 pages: $0.80 vs $1.31. Median time per resume: 46 s vs 138 s.
GLM 5.3 Flash wins on 137 of 297 resumes, Qwen 3.5 9B on 149, 11 tied.
59.36
GLM 5.3 Flash
A · Vision LLM
76.09
Qwen 3.5 9B
B · Vision LLM
Qwen 3.5 9B is ahead by 16.72 points on these 297 resumes.
- Many entries 81A 43.3 · B 74.0−30.7
- Long bullet lists 99A 42.9 · B 73.3−30.3
- Split across pages 83A 51.5 · B 73.5−22.0
- Big skills list 59A 64.6 · B 76.3−11.7
- Custom sections 103A 48.5 · B 73.1−24.6
- Combined headings 37A 65.7 · B 72.2−6.5
- Promotions 87A 59.2 · B 74.9−15.6
- Partial dates 137A 52.2 · B 75.7−23.5
- Overlapping jobs 68A 50.4 · B 72.3−21.8
- Accented text 13A 51.1 · B 83.7−32.6
Side by side
| GLM 5.3 Flash | Qwen 3.5 9B | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | Zhipu AI | Alibaba |
| Rank | 18 of 18 | 15 of 18 |
| F1 | 59.2 | 76.0 |
| Precision | 71.8 | 78.9 |
| Recall | 62.0 | 80.3 |
| Cost per 1,000 pages | $0.80 | $1.31 |
| Median time per resume | 46 s | 138 s |
| Resumes won | 137 | 149 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GLM 5.3 Flash | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Content as images (distractors) | 8 | 10.4 | 85.9 | −75.5 |
| Distractor layouts (source) | 18 | 17.8 | 80.4 | −62.5 |
| Wording traps (distractors) | 16 | 20.2 | 77.7 | −57.4 |
| Medium (length) | 90 | 24.2 | 78.0 | −53.8 |
| Expert-built (Canva / LaTeX) (source) | 32 | 42.9 | 79.1 | −36.3 |
| Typos kept on purpose (distractors) | 36 | 36.3 | 72.3 | −35.9 |
| Accented text (extraction challenges) | 13 | 51.1 | 83.7 | −32.6 |
| Many entries (extraction challenges) | 81 | 43.3 | 74.0 | −30.7 |
| Long bullet lists (extraction challenges) | 99 | 42.9 | 73.3 | −30.3 |
| Resume-builder templates (source) | 10 | 48.8 | 78.5 | −29.6 |
| References (noise) | 55 | 52.1 | 77.6 | −25.5 |
| Custom sections (extraction challenges) | 103 | 48.5 | 73.1 | −24.6 |
| Section | Resumes | GLM 5.3 Flash | Qwen 3.5 9B | Gap |
|---|---|---|---|---|
| Contact details | 297 | 73.5 | 92.5 | −19.0 |
| Experience | 297 | 55.6 | 77.2 | −21.6 |
| Education | 295 | 64.4 | 80.9 | −16.4 |
| Summary | 287 | 50.9 | 78.1 | −27.3 |
| Certifications | 243 | 57.6 | 74.6 | −17.1 |
| Awards | 102 | 53.9 | 54.8 | −1.0 |
| Skills | 284 | 65.9 | 83.3 | −17.4 |
| Languages | 178 | 65.8 | 79.9 | −14.1 |
| Custom sections | 211 | 32.1 | 36.4 | −4.4 |
| Interests | 74 | 44.3 | 84.3 | −40.0 |
| Volunteering | 79 | 43.0 | 81.2 | −38.2 |
| Profiles | 37 | 42.3 | 51.3 | −9.0 |
| Projects | 80 | 61.1 | 75.5 | −14.4 |
| Publications | 50 | 65.0 | 76.3 | −11.3 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GLM 5.3 Flash | Qwen 3.5 9B | Gap |
|---|---|---|---|
| Head of Events & Public Space Operations: Table grid with emoji bullets | 10.8 | 88.2 | −77.4 |
| Quality Systems Lead: Photo of a printout | 9.2 | 79.4 | −70.2 |
| Partner: Consulting CV, six pages | 10.3 | 77.9 | −67.7 |
| Head of Developer Experience (Internal title: Jedi Master of Analytics) : Unusual job titles | 17.3 | 77.2 | −59.9 |
Which to pick
Qwen 3.5 9B is more accurate. GLM 5.3 Flash costs 39% less for 16.8 fewer points.
GLM 5.3 Flash does better on handwritten and short. Qwen 3.5 9B does better on content as images, distractor layouts and wording traps.
GLM 5.3 Flash against every other model
- GLM 5.3 Flash vs LlamaParse Extract Agentic Plus
- GLM 5.3 Flash vs LlamaParse Extract Agentic
- GLM 5.3 Flash vs LlamaParse Extract Cost-Effective
- GLM 5.3 Flash vs Reducto Deep Extract
- GLM 5.3 Flash vs Reducto Extract
- GLM 5.3 Flash vs Extend Max Context
- GLM 5.3 Flash vs Extend Extract
- GLM 5.3 Flash vs GPT-5.6
- GLM 5.3 Flash vs GPT-5.5
- GLM 5.3 Flash vs GPT-5.4 Nano
- GLM 5.3 Flash vs Claude Opus 4.8
- GLM 5.3 Flash vs Gemini 3.5 Flash
- GLM 5.3 Flash vs Gemma 4 26B
- GLM 5.3 Flash vs Qwen 3.8 Flash
- GLM 5.3 Flash vs Qwen 3.8 27B
- GLM 5.3 Flash vs Qwen 3.5 35B
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 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
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