| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-classification-on-id-pattern-dataset | Claude 3 Opus | #1 | Percentage correct: 24.3% |
| image-classification-on-id-pattern-dataset | Gemini 1.5 Pro | #2 | Percentage correct: 39% |
| image-classification-on-id-pattern-dataset | GPT-4omni | #3 | Percentage correct: 42.1% |