Common Sense Reasoning On Parus
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| Model 1 | 0.574 |
| unreasonable-effectiveness-of-rule-based | 0.498 |
| russiansuperglue-a-russian-language | 0.486 |
| Model 4 | 0.908 |
| Model 5 | 0.508 |
| Model 6 | 0.766 |
| Model 7 | 0.528 |
| unreasonable-effectiveness-of-rule-based | 0.478 |
| Model 9 | 0.598 |
| Model 10 | 0.508 |
| Model 11 | 0.584 |
| mt5-a-massively-multilingual-pre-trained-text | 0.504 |
| unreasonable-effectiveness-of-rule-based | 0.48 |
| Model 14 | 0.562 |
| russiansuperglue-a-russian-language | 0.982 |
| Model 16 | 0.492 |
| Model 17 | 0.66 |
| Model 18 | 0.498 |
| Model 19 | 0.498 |
| Model 20 | 0.476 |
| Model 21 | 0.676 |
| Model 22 | 0.554 |