Skip to content
vs

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

+23.65A − B, points of F1

61.86

GPT-5.4 Nano

B · Vision LLM

A better on 275level on 1B better on 24

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 vs GPT-5.4 Nano
Claude Opus 4.8GPT-5.4 Nano
TypeVision LLMVision LLM
MakerAnthropicOpenAI
Rank4 of 1817 of 18
F185.561.9
Precision86.870.1
Recall87.566.3
Cost per 1,000 pages$90$2.76
Median time per resume31 s20 s
Resumes won27524

Claude Opus 4.8 in detailGPT-5.4 Nano in detail

Where each one wins

Where the two differ most.

Claude Opus 4.8 vs GPT-5.4 Nano by kind of resume
Kind of resume# of resumesClaude Opus 4.8GPT-5.4 NanoGap
Scanned & rotated (source)1987.56.3+81.2
Rotated & warped pages (distractors)2187.411.7+75.7
Hidden text & prompt injections (distractors)1490.822.0+68.8
Image only (reading the page)2877.021.0+56.0
Typos kept on purpose (distractors)3785.233.5+51.7
Two-column sidebar (layout)5481.947.4+34.5
Accented text (extraction challenges)1385.655.9+29.7
Sidebar or grid (reading the page)8284.254.9+29.4
Photo (reading the page)4586.359.4+26.9
Promotions (extraction challenges)8885.558.7+26.8
Expert-built (Canva / LaTeX) (source)3286.160.3+25.8
Medium (length)9085.860.2+25.6
Claude Opus 4.8 vs GPT-5.4 Nano by section
SectionResumesClaude Opus 4.8GPT-5.4 NanoGap
Contact details30093.781.2+12.5
Experience30088.263.7+24.6
Education29790.262.2+28.0
Summary29089.771.7+17.9
Certifications23985.453.6+31.8
Awards10672.944.9+28.0
Skills28395.274.8+20.5
Languages16785.869.0+16.8
Custom sections21851.626.3+25.3
Interests6393.770.0+23.7
Volunteering7884.659.9+24.7
Profiles3561.423.7+37.7
Projects7882.148.8+33.4
Publications5281.830.7+51.1

Published resumes they disagree on most

Open one to see both outputs field by field.

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

GPT-5.4 Nano against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, Claude Opus 4.8 or GPT-5.4 Nano?

Claude Opus 4.8: 85.5 F1 against 61.9.

Which is cheaper, Claude Opus 4.8 or GPT-5.4 Nano?

GPT-5.4 Nano: $2.76 per 1,000 pages against $90.

Where does each one do better?

Claude Opus 4.8: scanned & rotated, rotated & warped pages and hidden text & prompt injections.