logiqa
Unknown
OCR benchmark
2
Total Results
2
Models Tested
1
Metrics
2025-12-21
Last Updated
accuracy
Higher is better
| Rank | Model | Score | Source |
|---|---|---|---|
| 1 | gpt-4o Logical reasoning from Chinese Civil Service exams. | 56.3 | arxiv-paper |
| 2 | claude-35-sonnet | 53.8 | arxiv-paper |