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
84.75
GPT-5.6
B · Vision LLM
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 | GPT-5.6 | |
|---|---|---|
| Type | Vision LLM | Vision LLM |
| Maker | OpenAI | OpenAI |
| Rank | 11 of 18 | 6 of 18 |
| F1 | 83.5 | 84.7 |
| Precision | 84.9 | 85.9 |
| Recall | 86.0 | 87.2 |
| Cost per 1,000 pages | $87 | $74 |
| Median time per resume | 48 s | 38 s |
| Resumes won | 83 | 114 |
Where each one wins
Where the two differ most.
| Kind of resume | # of resumes | GPT-5.5 | GPT-5.6 | Gap |
|---|---|---|---|---|
| Scanned & rotated (source) | 19 | 60.7 | 71.6 | −10.9 |
| Rotated & warped pages (distractors) | 21 | 63.4 | 73.2 | −9.9 |
| Image only (reading the page) | 28 | 57.0 | 65.4 | −8.5 |
| Hidden text & prompt injections (distractors) | 14 | 69.1 | 77.5 | −8.4 |
| Typos kept on purpose (distractors) | 37 | 73.3 | 80.6 | −7.3 |
| Wording traps (distractors) | 16 | 85.3 | 89.1 | −3.8 |
| Distractor layouts (source) | 18 | 86.6 | 90.1 | −3.5 |
| Three-column (layout) | 20 | 82.6 | 85.6 | −3.0 |
| Accented text (extraction challenges) | 13 | 83.9 | 86.5 | −2.7 |
| Handwritten (reading the page) | 9 | 51.0 | 53.2 | −2.3 |
| Table grid (layout) | 8 | 96.8 | 94.5 | +2.2 |
| Short (length) | 148 | 85.2 | 87.2 | −1.9 |
| Section | Resumes | GPT-5.5 | GPT-5.6 | Gap |
|---|---|---|---|---|
| Contact details | 300 | 93.5 | 94.1 | −0.6 |
| Experience | 300 | 87.4 | 88.4 | −1.0 |
| Education | 297 | 88.7 | 91.9 | −3.1 |
| Summary | 291 | 81.8 | 83.4 | −1.7 |
| Certifications | 254 | 77.3 | 77.9 | −0.5 |
| Awards | 98 | 75.3 | 81.2 | −5.9 |
| Skills | 287 | 91.5 | 93.2 | −1.7 |
| Languages | 168 | 85.7 | 85.9 | −0.1 |
| Custom sections | 210 | 49.7 | 51.2 | −1.5 |
| Interests | 64 | 92.4 | 91.4 | +1.0 |
| Volunteering | 77 | 85.0 | 85.7 | −0.7 |
| Profiles | 36 | 68.5 | 69.4 | −0.9 |
| Projects | 79 | 86.4 | 88.2 | −1.8 |
| Publications | 51 | 82.5 | 77.8 | +4.7 |
Published resumes they disagree on most
Open one to see both outputs field by field.
| Resume | GPT-5.5 | GPT-5.6 | Gap |
|---|---|---|---|
| Head of Developer Experience (Internal title: Jedi Master of Analytics) : Unusual job titles | 80.2 | 93.6 | −13.5 |
| Quality Systems Lead: Photo of a printout | 76.8 | 89.4 | −12.6 |
| Deputy Head of Mission: Rotated scan with hidden identity text | 64.7 | 76.2 | −11.5 |
| Head of Events & Public Space Operations: Table grid with emoji bullets | 99.5 | 90.0 | +9.5 |
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-5.5 vs LlamaParse Extract Agentic Plus
- GPT-5.5 vs LlamaParse Extract Agentic
- GPT-5.5 vs LlamaParse Extract Cost-Effective
- GPT-5.5 vs Reducto Deep Extract
- GPT-5.5 vs Reducto Extract
- GPT-5.5 vs Extend Max Context
- GPT-5.5 vs Extend Extract
- GPT-5.5 vs GPT-5.4 Nano
- GPT-5.5 vs Claude Opus 4.8
- GPT-5.5 vs Gemini 3.5 Flash
- GPT-5.5 vs Gemma 4 26B
- GPT-5.5 vs Qwen 3.8 Flash
- GPT-5.5 vs Qwen 3.8 27B
- GPT-5.5 vs Qwen 3.5 35B
- GPT-5.5 vs Qwen 3.5 9B
- GPT-5.5 vs GLM 5.3 Flash
GPT-5.6 against every other model
- GPT-5.6 vs LlamaParse Extract Agentic Plus
- GPT-5.6 vs LlamaParse Extract Agentic
- GPT-5.6 vs LlamaParse Extract Cost-Effective
- GPT-5.6 vs Reducto Deep Extract
- GPT-5.6 vs Reducto Extract
- GPT-5.6 vs Extend Max Context
- GPT-5.6 vs Extend Extract
- GPT-5.6 vs GPT-5.4 Nano
- GPT-5.6 vs Claude Opus 4.8
- GPT-5.6 vs Gemini 3.5 Flash
- GPT-5.6 vs Gemma 4 26B
- GPT-5.6 vs Qwen 3.8 Flash
- GPT-5.6 vs Qwen 3.8 27B
- GPT-5.6 vs Qwen 3.5 35B
- GPT-5.6 vs Qwen 3.5 9B
- GPT-5.6 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