Closed
GPT-5-Mini
OpenAI128K context$0.8/1K pages2026-01-20
Overall Rank
#7
of 16 models
Overall Score
70.8
avg across benchmarks
Best Task
Formula
86.7
Weakest Task
Visual QA
65.0
Benchmark Performance
OlmOCR Benchv1.0
10/16
| Overall | Math | Table | Present | Absent | Order |
|---|---|---|---|---|---|
| 56.7 | 51.5 | 70.6 | 70.2 | 26.1 | 74.4 |
OmniDocBenchv1.5
8/16
| Overall | Text Edit↓ | Formula CDM↑ | Table TEDS↑ | TEDS-S↑ | Read Order↓ |
|---|---|---|---|---|---|
| 82.5 | 0.138 | 86.7 | 74.6 | 80.1 | 0.121 |
IDP Core Benchv1.0
8/16
| Overall | KIE | OCR | Table | VQA |
|---|---|---|---|---|
| 73.3 | 85.7 | 73.0 | 69.5 | 65.0 |
Capability Profile
Strength Analysis
Auto-generated from benchmark scores
Strengths
- Formula86.7
- Text Extraction86.2
Weaknesses
- Visual QA65.0
- Table Understanding71.6