Gemini 3.5 Flash vs LlamaParse Extract Agentic Plus: which is better at resume extraction?
LlamaParse Extract Agentic Plus leads Gemini 3.5 Flash by 1.7 points (87.2 vs 85.5 F1). Cost per 1,000 pages: $35 vs $54. Median time per resume: 43 s vs 70 s.
Gemini 3.5 Flash wins on 99 of 300 resumes, LlamaParse Extract Agentic Plus on 145, 56 tied.
85.45
Gemini 3.5 Flash
A · Vision LLM
87.16
LlamaParse Extract Agentic Plus
B · Document API
LlamaParse Extract Agentic Plus is ahead by 1.71 points on these 300 resumes.
- Many entries 83A 84.3 · B 85.0−0.8
- Long bullet lists 101A 83.9 · B 84.9−1.1
- Split across pages 85A 84.6 · B 85.3−0.8
- Big skills list 60A 86.0 · B 86.0+0.0
- Custom sections 105A 83.6 · B 85.1−1.5
- Combined headings 37A 84.2 · B 84.6−0.4
- Promotions 88A 87.3 · B 87.4−0.0
- Partial dates 138A 84.9 · B 87.0−2.0
- Overlapping jobs 69A 86.4 · B 84.1+2.4
- Accented text 13A 86.4 · B 92.0−5.6
Side by side
| Gemini 3.5 Flash | LlamaParse Extract Agentic Plus | |
|---|---|---|
| Type | Vision LLM | Document API |
| Maker | LlamaIndex | |
| Rank | 5 of 18 | 1 of 18 |
| F1 | 85.5 | 87.2 |
| Precision | 86.9 | 88.4 |
| Recall | 87.9 | 88.3 |
| Cost per 1,000 pages | $35 | $54 |
| Median time per resume | 43 s | 70 s |
| Resumes won | 99 | 145 |
Gemini 3.5 Flash in detailLlamaParse Extract Agentic Plus in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Gemini 3.5 Flash | LlamaParse Extract Agentic Plus | Gap |
|---|---|---|---|---|
| Handwritten (reading the page) | 9 | 50.3 | 67.8 | −17.5 |
| Content as images (distractors) | 8 | 76.7 | 93.9 | −17.2 |
| Image only (reading the page) | 28 | 75.1 | 84.2 | −9.1 |
| Wording traps (distractors) | 16 | 80.4 | 89.0 | −8.6 |
| Distractor layouts (source) | 18 | 81.4 | 89.9 | −8.5 |
| Typos kept on purpose (distractors) | 37 | 84.4 | 91.4 | −7.0 |
| Hidden text & prompt injections (distractors) | 14 | 86.7 | 93.2 | −6.5 |
| Accented text (extraction challenges) | 13 | 86.4 | 92.0 | −5.6 |
| Scanned & rotated (source) | 19 | 87.2 | 92.8 | −5.6 |
| Rotated & warped pages (distractors) | 21 | 87.4 | 92.5 | −5.1 |
| References (noise) | 55 | 90.7 | 87.6 | +3.1 |
| Table grid (layout) | 8 | 95.0 | 98.1 | −3.1 |
| Section | Resumes | Gemini 3.5 Flash | LlamaParse Extract Agentic Plus | Gap |
|---|---|---|---|---|
| Contact details | 300 | 95.3 | 94.3 | +0.9 |
| Experience | 300 | 86.5 | 91.5 | −5.1 |
| Education | 297 | 91.5 | 93.3 | −1.8 |
| Summary | 290 | 89.3 | 84.8 | +4.5 |
| Certifications | 245 | 84.0 | 85.8 | −1.8 |
| Awards | 92 | 80.3 | 84.1 | −3.8 |
| Skills | 289 | 93.5 | 97.6 | −4.1 |
| Languages | 170 | 84.3 | 84.6 | −0.3 |
| Custom sections | 216 | 50.1 | 52.2 | −2.1 |
| Interests | 63 | 94.2 | 93.0 | +1.2 |
| Volunteering | 79 | 83.7 | 89.6 | −5.8 |
| Profiles | 35 | 64.8 | 73.3 | −8.6 |
| Projects | 80 | 80.4 | 87.0 | −6.6 |
| Publications | 52 | 83.4 | 85.5 | −2.2 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Gemini 3.5 Flash | LlamaParse Extract Agentic Plus | Gap |
|---|---|---|---|
| senior Consultant - package Implementation: Handwritten resume | 42.1 | 78.1 | −36.0 |
| Senior ocularist and practice owner: Handwritten resume, six pages | 39.8 | 74.0 | −34.2 |
| Head of Events & Public Space Operations: Table grid with emoji bullets | 76.7 | 98.4 | −21.7 |
| Senior Full-Stack Engineer: LaTeX CV with a running header | 58.8 | 77.0 | −18.2 |
Which to pick
LlamaParse Extract Agentic Plus is more accurate. Gemini 3.5 Flash costs 35% less for 1.7 fewer points.
Gemini 3.5 Flash does better on references, overlapping jobs and resume-builder templates. LlamaParse Extract Agentic Plus does better on handwritten, content as images and image only.
Gemini 3.5 Flash against every other model
- Gemini 3.5 Flash vs LlamaParse Extract Agentic
- 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 Plus against every other model
- LlamaParse Extract Agentic Plus vs LlamaParse Extract Agentic
- LlamaParse Extract Agentic Plus vs LlamaParse Extract Cost-Effective
- LlamaParse Extract Agentic Plus vs Reducto Deep Extract
- LlamaParse Extract Agentic Plus vs Reducto Extract
- LlamaParse Extract Agentic Plus vs Extend Max Context
- LlamaParse Extract Agentic Plus vs Extend Extract
- LlamaParse Extract Agentic Plus vs GPT-5.6
- LlamaParse Extract Agentic Plus vs GPT-5.5
- LlamaParse Extract Agentic Plus vs GPT-5.4 Nano
- LlamaParse Extract Agentic Plus vs Claude Opus 4.8
- LlamaParse Extract Agentic Plus vs Gemma 4 26B
- LlamaParse Extract Agentic Plus vs Qwen 3.8 Flash
- LlamaParse Extract Agentic Plus vs Qwen 3.8 27B
- LlamaParse Extract Agentic Plus vs Qwen 3.5 35B
- LlamaParse Extract Agentic Plus vs Qwen 3.5 9B
- LlamaParse Extract Agentic Plus 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