6,138 reading comprehension questions requiring logical reasoning from GMAT/LSAT exams.
Accuracy is the reported evaluation metric for ReClor. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
| Rank | Model | Trust | Score | Year | Links | Edit |
|---|---|---|---|---|---|---|
| 01 | gpt-4o | paper | 72.4 | 2025 | Source ↗ | Edit result |
| 02 | claude-35-sonnet | paper | 68.9 | 2025 | Source ↗ | Edit result |
| 03 | Claude 3.5 Sonnet | paper | 68.9 | 2025 | Source ↗ | Edit result |