Skip to content
vs

GPT-5.5 vs GPT-5.6: which is better at resume extraction?

GPT-5.6 leads GPT-5.5 by 1.2 points (84.7 vs 83.5 F1). Cost per 1,000 pages: $87 vs $74. Median time per resume: 48 s vs 38 s.

GPT-5.5 wins on 83 of 300 resumes, GPT-5.6 on 114, 103 tied.

83.50

GPT-5.5

A · Vision LLM

−1.25A − B, points of F1

84.75

GPT-5.6

B · Vision LLM

A better on 83level on 103B better on 114

GPT-5.6 is ahead by 1.25 points on these 300 resumes.

  • Many entries 83A 83.8 · B 84.5−0.7
  • Long bullet lists 101A 84.3 · B 84.9−0.6
  • Split across pages 85A 85.0 · B 84.9+0.2
  • Big skills list 60A 85.5 · B 85.2+0.3
  • Custom sections 105A 80.8 · B 82.2−1.3
  • Combined headings 37A 83.4 · B 84.1−0.7
  • Promotions 88A 84.0 · B 85.0−1.0
  • Partial dates 138A 84.0 · B 85.7−1.6
  • Overlapping jobs 69A 82.1 · B 83.2−1.1
  • Accented text 13A 83.9 · B 86.5−2.7

Side by side

GPT-5.5 vs GPT-5.6
GPT-5.5GPT-5.6
TypeVision LLMVision LLM
MakerOpenAIOpenAI
Rank11 of 186 of 18
F183.584.7
Precision84.985.9
Recall86.087.2
Cost per 1,000 pages$87$74
Median time per resume48 s38 s
Resumes won83114

GPT-5.5 in detailGPT-5.6 in detail

Where each one wins

Where the two differ most.

GPT-5.5 vs GPT-5.6 by kind of resume
Kind of resume# of resumesGPT-5.5GPT-5.6Gap
Scanned & rotated (source)1960.771.6−10.9
Rotated & warped pages (distractors)2163.473.2−9.9
Image only (reading the page)2857.065.4−8.5
Hidden text & prompt injections (distractors)1469.177.5−8.4
Typos kept on purpose (distractors)3773.380.6−7.3
Wording traps (distractors)1685.389.1−3.8
Distractor layouts (source)1886.690.1−3.5
Three-column (layout)2082.685.6−3.0
Accented text (extraction challenges)1383.986.5−2.7
Handwritten (reading the page)951.053.2−2.3
Table grid (layout)896.894.5+2.2
Short (length)14885.287.2−1.9
GPT-5.5 vs GPT-5.6 by section
SectionResumesGPT-5.5GPT-5.6Gap
Contact details30093.594.1−0.6
Experience30087.488.4−1.0
Education29788.791.9−3.1
Summary29181.883.4−1.7
Certifications25477.377.9−0.5
Awards9875.381.2−5.9
Skills28791.593.2−1.7
Languages16885.785.9−0.1
Custom sections21049.751.2−1.5
Interests6492.491.4+1.0
Volunteering7785.085.7−0.7
Profiles3668.569.4−0.9
Projects7986.488.2−1.8
Publications5182.577.8+4.7

Published resumes they disagree on most

Open one to see both outputs field by field.

Which to pick

GPT-5.6 is ahead on accuracy, cost and speed.

GPT-5.5 does better on table grid and references. GPT-5.6 does better on scanned & rotated, rotated & warped pages and image only.

GPT-5.5 against every other model

GPT-5.6 against every other model

Popular comparisons

Frequently asked questions (FAQs)

Which is better for resume extraction, GPT-5.5 or GPT-5.6?

GPT-5.6: 84.7 F1 against 83.5.

Which is cheaper, GPT-5.5 or GPT-5.6?

GPT-5.6: $74 per 1,000 pages against $87.

Where does each one do better?

GPT-5.5: table grid and references. GPT-5.6: scanned & rotated, rotated & warped pages and image only.