Commonsense Reasoning on CommonsenseQA (CSQA)
79Accuracy
Latent Thinking Optimization
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.09 | 79 | |
2025.09 | 78.6 | |
2025.09 | 74.2 | |
2025.05 | 70.2 | |
2025.05 | 67.7 | |
2025.05 | 66.3 | |
2025.09 | 65 | |
2025.05 | 63.3 | |
2025.09 | 60.6 | |
2025.05 | 58.8 | |
2025.12 | 53 | |
2025.12 | 52 | |
2025.12 | 51 | |
2025.12 | 51 | |
2025.12 | 51 | |
2025.09 | 50.1 | |
2025.12 | 50 | |
2025.12 | 50 | |
2025.09 | 49.3 | |
2025.12 | 49 | |
2025.12 | 49 | |
2025.12 | 47 | |
2025.12 | 46 | |
2025.12 | 46 | |
2025.12 | 44 | |
2025.12 | 44 | |
2025.12 | 42 | |
2025.05 | 41.1 | |
2025.12 | 41 | |
2025.12 | 40 | |
2025.09 | 39.9 | |
2025.09 | 39.8 | |
2025.12 | 36 | |
2025.12 | 36 | |
2025.12 | 30 | |
2025.12 | 28 | |
2025.12 | 20 | |
2025.05 | 19.1 |