Gemini 3.5 Flash vs LlamaParse Extract Agentic: which is better at resume extraction?
LlamaParse Extract Agentic leads Gemini 3.5 Flash by 0.1 points (85.5 vs 85.5 F1). Cost per 1,000 pages: $35 vs $23. Median time per resume: 43 s vs 55 s.
Gemini 3.5 Flash wins on 128 of 300 resumes, LlamaParse Extract Agentic on 121, 51 tied.
85.45
Gemini 3.5 Flash
A · Vision LLM
85.55
LlamaParse Extract Agentic
B · Document API
LlamaParse Extract Agentic is ahead by 0.09 points on these 300 resumes.
- Many entries 83A 84.3 · B 83.0+1.2
- Long bullet lists 101A 83.9 · B 83.1+0.7
- Split across pages 85A 84.6 · B 83.8+0.8
- Big skills list 60A 86.0 · B 83.7+2.3
- Custom sections 105A 83.6 · B 82.5+1.1
- Combined headings 37A 84.2 · B 83.2+1.0
- Promotions 88A 87.3 · B 85.5+1.8
- Partial dates 138A 84.9 · B 85.6−0.6
- Overlapping jobs 69A 86.4 · B 83.5+2.9
- Accented text 13A 86.4 · B 91.1−4.8
Side by side
| Gemini 3.5 Flash | LlamaParse Extract Agentic | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | LlamaIndex | |
| Rank | 5 of 18 | 3 of 18 |
| F1 | 85.5 | 85.5 |
| Precision | 86.9 | 86.8 |
| Recall | 87.9 | 87.3 |
| Cost per 1,000 pages | $35 | $23 |
| Median time per resume | 43 s | 55 s |
| Resumes won | 128 | 121 |
Gemini 3.5 Flash in detailLlamaParse Extract Agentic in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Gemini 3.5 Flash | LlamaParse Extract Agentic | Gap |
|---|---|---|---|---|
| Content as images (distractors) | 8 | 76.7 | 91.6 | −14.9 |
| Handwritten (reading the page) | 9 | 50.3 | 63.5 | −13.2 |
| Wording traps (distractors) | 16 | 80.4 | 87.7 | −7.3 |
| Distractor layouts (source) | 18 | 81.4 | 88.3 | −6.9 |
| Image only (reading the page) | 28 | 75.1 | 81.5 | −6.4 |
| Typos kept on purpose (distractors) | 37 | 84.4 | 90.0 | −5.6 |
| Hidden text & prompt injections (distractors) | 14 | 86.7 | 91.6 | −4.9 |
| Accented text (extraction challenges) | 13 | 86.4 | 91.1 | −4.8 |
| References (noise) | 55 | 90.7 | 86.2 | +4.5 |
| Scanned & rotated (source) | 19 | 87.2 | 91.6 | −4.4 |
| Rotated & warped pages (distractors) | 21 | 87.4 | 90.9 | −3.5 |
| Resume-builder templates (source) | 10 | 86.4 | 83.2 | +3.2 |
| Section | Resumes | Gemini 3.5 Flash | LlamaParse Extract Agentic | Gap |
|---|---|---|---|---|
| Contact details | 300 | 95.3 | 94.5 | +0.7 |
| Experience | 300 | 86.5 | 89.6 | −3.1 |
| Education | 297 | 91.5 | 91.3 | +0.2 |
| Summary | 290 | 89.3 | 84.5 | +4.8 |
| Certifications | 245 | 84.0 | 80.9 | +3.0 |
| Awards | 92 | 80.3 | 80.3 | +0.0 |
| Skills | 289 | 93.5 | 95.1 | −1.6 |
| Languages | 170 | 84.3 | 84.2 | +0.2 |
| Custom sections | 216 | 50.1 | 52.1 | −2.0 |
| Interests | 63 | 94.2 | 93.0 | +1.2 |
| Volunteering | 79 | 83.7 | 87.7 | −3.9 |
| Profiles | 35 | 64.8 | 67.6 | −2.9 |
| Projects | 80 | 80.4 | 86.2 | −5.8 |
| Publications | 52 | 83.4 | 80.5 | +2.8 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Gemini 3.5 Flash | LlamaParse Extract Agentic | Gap |
|---|---|---|---|
| senior Consultant - package Implementation: Handwritten resume | 42.1 | 74.0 | −31.9 |
| Senior ocularist and practice owner: Handwritten resume, six pages | 39.8 | 70.4 | −30.6 |
| Senior Data Scientist (Lead): Fifty skills, seven pages | 95.8 | 73.9 | +21.9 |
| Head of Events & Public Space Operations: Table grid with emoji bullets | 76.7 | 98.4 | −21.7 |
Which to pick
LlamaParse Extract Agentic is more accurate. Gemini 3.5 Flash is the faster of the two.
Gemini 3.5 Flash does better on references, resume-builder templates and overlapping jobs. LlamaParse Extract Agentic does better on content as images, handwritten and wording traps.
Gemini 3.5 Flash against every other model
- Gemini 3.5 Flash vs LlamaParse Extract Agentic Plus
- Gemini 3.5 Flash vs LlamaParse Extract Cost-Effective
- Gemini 3.5 Flash vs Reducto Deep Extract
- Gemini 3.5 Flash vs Reducto Extract
- Gemini 3.5 Flash vs Extend Max Context
- Gemini 3.5 Flash vs Extend Extract
- Gemini 3.5 Flash vs GPT-5.6
- Gemini 3.5 Flash vs GPT-5.5
- Gemini 3.5 Flash vs GPT-5.4 Nano
- Gemini 3.5 Flash vs Claude Opus 4.8
- Gemini 3.5 Flash vs Gemma 4 26B
- Gemini 3.5 Flash vs Qwen 3.8 Flash
- Gemini 3.5 Flash vs Qwen 3.8 27B
- Gemini 3.5 Flash vs Qwen 3.5 35B
- Gemini 3.5 Flash vs Qwen 3.5 9B
- Gemini 3.5 Flash vs GLM 5.3 Flash
LlamaParse Extract Agentic against every other model
- LlamaParse Extract Agentic vs LlamaParse Extract Agentic Plus
- LlamaParse Extract Agentic vs LlamaParse Extract Cost-Effective
- LlamaParse Extract Agentic vs Reducto Deep Extract
- LlamaParse Extract Agentic vs Reducto Extract
- LlamaParse Extract Agentic vs Extend Max Context
- LlamaParse Extract Agentic vs Extend Extract
- LlamaParse Extract Agentic vs GPT-5.6
- LlamaParse Extract Agentic vs GPT-5.5
- LlamaParse Extract Agentic vs GPT-5.4 Nano
- LlamaParse Extract Agentic vs Claude Opus 4.8
- LlamaParse Extract Agentic vs Gemma 4 26B
- LlamaParse Extract Agentic vs Qwen 3.8 Flash
- LlamaParse Extract Agentic vs Qwen 3.8 27B
- LlamaParse Extract Agentic vs Qwen 3.5 35B
- LlamaParse Extract Agentic vs Qwen 3.5 9B
- LlamaParse Extract Agentic 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