Closed
GPT-5.2
OpenAI128K context$3.5/1K pages2026-01-20
Overall Rank
#6
of 16 models
Overall Score
79.2
avg across benchmarks
Best Task
Formula
90.1
Weakest Task
Visual QA
63.5
Benchmark Performance
OlmOCR Benchv1.0
6/16
| Overall | Math | Table | Present | Absent | Order |
|---|---|---|---|---|---|
| 72.2 | 79.3 | 86.8 | 68.9 | 27.1 | 72.7 |
OmniDocBenchv1.5
4/16
| Overall | Text Edit↓ | Formula CDM↑ | Table TEDS↑ | TEDS-S↑ | Read Order↓ |
|---|---|---|---|---|---|
| 88.0 | 0.111 | 90.1 | 84.9 | 89.5 | 0.098 |
IDP Core Benchv1.0
5/16
| Overall | KIE | OCR | Table | VQA |
|---|---|---|---|---|
| 77.4 | 87.5 | 72.8 | 86.0 | 63.5 |
Capability Profile
Strength Analysis
Auto-generated from benchmark scores
Strengths
- Formula90.1
- Text Extraction88.9
Weaknesses
- Visual QA63.5
- Layout & Order81.5