LlamaParse Extract Agentic vs LlamaParse Extract Agentic Plus: which is better at resume extraction?
LlamaParse Extract Agentic Plus leads LlamaParse Extract Agentic by 1.6 points (87.2 vs 85.5 F1). Cost per 1,000 pages: $23 vs $54. Median time per resume: 55 s vs 70 s.
LlamaParse Extract Agentic wins on 90 of 300 resumes, LlamaParse Extract Agentic Plus on 138, 72 tied.
85.55
LlamaParse Extract Agentic
A · Document API
87.16
LlamaParse Extract Agentic Plus
B · Document API
LlamaParse Extract Agentic Plus is ahead by 1.61 points on these 300 resumes.
- Many entries 83A 83.0 · B 85.0−2.0
- Long bullet lists 101A 83.1 · B 84.9−1.8
- Split across pages 85A 83.8 · B 85.3−1.6
- Big skills list 60A 83.7 · B 86.0−2.3
- Custom sections 105A 82.5 · B 85.1−2.6
- Combined headings 37A 83.2 · B 84.6−1.4
- Promotions 88A 85.5 · B 87.4−1.8
- Partial dates 138A 85.6 · B 87.0−1.4
- Overlapping jobs 69A 83.5 · B 84.1−0.6
- Accented text 13A 91.1 · B 92.0−0.8
Side by side
| LlamaParse Extract Agentic | LlamaParse Extract Agentic Plus | |
|---|---|---|
| Type | Document API | Document API |
| Maker | LlamaIndex | LlamaIndex |
| Rank | 3 of 18 | 1 of 18 |
| F1 | 85.5 | 87.2 |
| Precision | 86.8 | 88.4 |
| Recall | 87.3 | 88.3 |
| Cost per 1,000 pages | $23 | $54 |
| Median time per resume | 55 s | 70 s |
| Resumes won | 90 | 138 |
LlamaParse Extract Agentic in detailLlamaParse Extract Agentic Plus in detail
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | LlamaParse Extract Agentic | LlamaParse Extract Agentic Plus | Gap |
|---|---|---|---|---|
| Handwritten (reading the page) | 9 | 63.5 | 67.8 | −4.4 |
| Photo (reading the page) | 45 | 84.7 | 88.1 | −3.4 |
| Repeated header (noise) | 67 | 86.2 | 89.3 | −3.0 |
| Medium (length) | 90 | 84.4 | 87.4 | −2.9 |
| Table grid (layout) | 8 | 95.2 | 98.1 | −2.9 |
| Image only (reading the page) | 28 | 81.5 | 84.2 | −2.7 |
| Expert-built (Canva / LaTeX) (source) | 32 | 83.7 | 86.4 | −2.6 |
| Custom sections (extraction challenges) | 105 | 82.5 | 85.1 | −2.6 |
| Resume-builder templates (source) | 10 | 83.2 | 85.6 | −2.4 |
| Content as images (distractors) | 8 | 91.6 | 93.9 | −2.3 |
| Big skills list (extraction challenges) | 60 | 83.7 | 86.0 | −2.3 |
| Three-column (layout) | 20 | 85.4 | 87.6 | −2.2 |
| Section | Resumes | LlamaParse Extract Agentic | LlamaParse Extract Agentic Plus | Gap |
|---|---|---|---|---|
| Contact details | 300 | 94.5 | 94.3 | +0.2 |
| Experience | 300 | 89.6 | 91.5 | −2.0 |
| Education | 297 | 91.3 | 93.3 | −2.0 |
| Summary | 290 | 84.5 | 84.8 | −0.3 |
| Certifications | 252 | 80.9 | 85.8 | −4.9 |
| Awards | 93 | 80.3 | 84.1 | −3.9 |
| Skills | 286 | 95.1 | 97.6 | −2.5 |
| Languages | 167 | 84.2 | 84.6 | −0.5 |
| Custom sections | 208 | 52.1 | 52.2 | −0.0 |
| Interests | 64 | 93.0 | 93.0 | −0.0 |
| Volunteering | 77 | 87.7 | 89.6 | −1.9 |
| Profiles | 35 | 67.6 | 73.3 | −5.7 |
| Projects | 78 | 86.2 | 87.0 | −0.8 |
| Publications | 51 | 80.5 | 85.5 | −5.0 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | LlamaParse Extract Agentic | LlamaParse Extract Agentic Plus | Gap |
|---|---|---|---|
| Senior Data Scientist (Lead): Fifty skills, seven pages | 73.9 | 97.7 | −23.8 |
| Senior Controls Engineer: Five custom sections | 89.6 | 78.3 | +11.3 |
| Senior Full-Stack Engineer: LaTeX CV with a running header | 66.9 | 77.0 | −10.1 |
| Quality Systems Lead: Photo of a printout | 80.0 | 90.0 | −10.0 |
Which to pick
LlamaParse Extract Agentic Plus is more accurate. LlamaParse Extract Agentic costs 57% less for 1.6 fewer points.
LlamaParse Extract Agentic does better on busy page. LlamaParse Extract Agentic Plus does better on handwritten, photo and repeated header.
LlamaParse Extract Agentic against every other model
- 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 Gemini 3.5 Flash
- 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
LlamaParse Extract Agentic Plus against every other model
- 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 Gemini 3.5 Flash
- 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
- Reducto Deep Extract vs Reducto Extract
- Gemma 4 26B vs Qwen 3.8 27B
- Document APIs vs vision LLMs