Claude Opus 4.8 vs GPT-5.4 Nano: which is better at resume extraction?
Claude Opus 4.8 leads GPT-5.4 Nano by 23.6 points (85.5 vs 61.9 F1). Cost per 1,000 pages: $90 vs $2.76. Median time per resume: 31 s vs 20 s.
Claude Opus 4.8 wins on 275 of 300 resumes, GPT-5.4 Nano on 24, 1 tied.
85.51
Claude Opus 4.8
A · Vision LLM
61.86
GPT-5.4 Nano
B · Vision LLM
Claude Opus 4.8 is ahead by 23.65 points on these 300 resumes.
- Many entries 83A 83.7 · B 59.7+24.0
- Long bullet lists 101A 83.1 · B 61.0+22.1
- Split across pages 85A 84.6 · B 61.7+22.9
- Big skills list 60A 84.8 · B 64.9+19.9
- Custom sections 105A 83.4 · B 59.5+23.9
- Combined headings 37A 85.1 · B 64.6+20.5
- Promotions 88A 85.5 · B 58.7+26.8
- Partial dates 138A 84.5 · B 62.6+21.9
- Overlapping jobs 69A 83.5 · B 58.6+24.8
- Accented text 13A 85.6 · B 55.9+29.7
Side by side
| Claude Opus 4.8 | GPT-5.4 Nano | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | Anthropic | OpenAI |
| Rank | 4 of 18 | 17 of 18 |
| F1 | 85.5 | 61.9 |
| Precision | 86.8 | 70.1 |
| Recall | 87.5 | 66.3 |
| Cost per 1,000 pages | $90 | $2.76 |
| Median time per resume | 31 s | 20 s |
| Resumes won | 275 | 24 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | Claude Opus 4.8 | GPT-5.4 Nano | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 87.5 | 6.3 | +81.2 |
| Rotated & warped pages (distractors) | 21 | 87.4 | 11.7 | +75.7 |
| Hidden text & prompt injections (distractors) | 14 | 90.8 | 22.0 | +68.8 |
| Image only (reading the page) | 28 | 77.0 | 21.0 | +56.0 |
| Typos kept on purpose (distractors) | 37 | 85.2 | 33.5 | +51.7 |
| Two-column sidebar (layout) | 54 | 81.9 | 47.4 | +34.5 |
| Accented text (extraction challenges) | 13 | 85.6 | 55.9 | +29.7 |
| Sidebar or grid (reading the page) | 82 | 84.2 | 54.9 | +29.4 |
| Photo (reading the page) | 45 | 86.3 | 59.4 | +26.9 |
| Promotions (extraction challenges) | 88 | 85.5 | 58.7 | +26.8 |
| Expert-built (Canva / LaTeX) (source) | 32 | 86.1 | 60.3 | +25.8 |
| Medium (length) | 90 | 85.8 | 60.2 | +25.6 |
| Section | Resumes | Claude Opus 4.8 | GPT-5.4 Nano | Gap |
|---|---|---|---|---|
| Contact details | 300 | 93.7 | 81.2 | +12.5 |
| Experience | 300 | 88.2 | 63.7 | +24.6 |
| Education | 297 | 90.2 | 62.2 | +28.0 |
| Summary | 290 | 89.7 | 71.7 | +17.9 |
| Certifications | 239 | 85.4 | 53.6 | +31.8 |
| Awards | 106 | 72.9 | 44.9 | +28.0 |
| Skills | 283 | 95.2 | 74.8 | +20.5 |
| Languages | 167 | 85.8 | 69.0 | +16.8 |
| Custom sections | 218 | 51.6 | 26.3 | +25.3 |
| Interests | 63 | 93.7 | 70.0 | +23.7 |
| Volunteering | 78 | 84.6 | 59.9 | +24.7 |
| Profiles | 35 | 61.4 | 23.7 | +37.7 |
| Projects | 78 | 82.1 | 48.8 | +33.4 |
| Publications | 52 | 81.8 | 30.7 | +51.1 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | Claude Opus 4.8 | GPT-5.4 Nano | Gap |
|---|---|---|---|
| Deputy Head of Mission: Rotated scan with hidden identity text | 85.9 | 1.7 | +84.2 |
| Supervisory Human Resources Specialist, GS-0201-15: Resume-builder template | 82.8 | 32.5 | +50.4 |
| Partner: Consulting CV, six pages | 75.8 | 27.8 | +48.0 |
| Head of Digital Marketing: Canva design with a photo | 85.6 | 39.3 | +46.3 |
Which to pick
Claude Opus 4.8 is more accurate. GPT-5.4 Nano costs 97% less for 23.6 fewer points.
Claude Opus 4.8 does better on scanned & rotated, rotated & warped pages and hidden text & prompt injections.
Claude Opus 4.8 against every other model
- Claude Opus 4.8 vs LlamaParse Extract Agentic Plus
- Claude Opus 4.8 vs LlamaParse Extract Agentic
- Claude Opus 4.8 vs LlamaParse Extract Cost-Effective
- Claude Opus 4.8 vs Reducto Deep Extract
- Claude Opus 4.8 vs Reducto Extract
- Claude Opus 4.8 vs Extend Max Context
- Claude Opus 4.8 vs Extend Extract
- Claude Opus 4.8 vs GPT-5.6
- Claude Opus 4.8 vs GPT-5.5
- Claude Opus 4.8 vs Gemini 3.5 Flash
- Claude Opus 4.8 vs Gemma 4 26B
- Claude Opus 4.8 vs Qwen 3.8 Flash
- Claude Opus 4.8 vs Qwen 3.8 27B
- Claude Opus 4.8 vs Qwen 3.5 35B
- Claude Opus 4.8 vs Qwen 3.5 9B
- Claude Opus 4.8 vs GLM 5.3 Flash
GPT-5.4 Nano against every other model
- GPT-5.4 Nano vs LlamaParse Extract Agentic Plus
- GPT-5.4 Nano vs LlamaParse Extract Agentic
- GPT-5.4 Nano vs LlamaParse Extract Cost-Effective
- GPT-5.4 Nano vs Reducto Deep Extract
- GPT-5.4 Nano vs Reducto Extract
- GPT-5.4 Nano vs Extend Max Context
- GPT-5.4 Nano vs Extend Extract
- GPT-5.4 Nano vs GPT-5.6
- GPT-5.4 Nano vs GPT-5.5
- GPT-5.4 Nano vs Gemini 3.5 Flash
- GPT-5.4 Nano vs Gemma 4 26B
- GPT-5.4 Nano vs Qwen 3.8 Flash
- GPT-5.4 Nano vs Qwen 3.8 27B
- GPT-5.4 Nano vs Qwen 3.5 35B
- GPT-5.4 Nano vs Qwen 3.5 9B
- GPT-5.4 Nano 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