Closed
GPT-4.1
OpenAI1048K context$2/1K pages2025-04-14
Overall Rank
#8
of 16 models
Overall Score
70.0
avg across benchmarks
Best Task
Key Information Extraction
87.1
Weakest Task
Visual QA
63.0
Benchmark Performance
OlmOCR Benchv1.0
12/16
| Overall | Math | Table | Present | Absent | Order |
|---|---|---|---|---|---|
| 55.5 | 60.0 | 59.1 | 47.3 | 34.9 | 59.4 |
OmniDocBenchv1.5
9/16
| Overall | Text Edit↓ | Formula CDM↑ | Table TEDS↑ | TEDS-S↑ | Read Order↓ |
|---|---|---|---|---|---|
| 79.9 | 0.167 | 82.2 | 74.0 | 83.8 | 0.115 |
IDP Core Benchv1.0
6/16
| Overall | KIE | OCR | Table | VQA |
|---|---|---|---|---|
| 74.7 | 87.1 | 75.6 | 73.1 | 63.0 |
Capability Profile
Strength Analysis
Auto-generated from benchmark scores
Strengths
- Key Information Extraction87.1
- Text Extraction83.3
Weaknesses
- Visual QA63.0
- Table Understanding68.7