Logical Reasoning On Big Bench Logic Grid
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| palm-2-technical-report-1 | 36.5 |
| palm-2-technical-report-1 | 42.4 |
| scaling-language-models-methods-analysis-1 | 35.1 |
| training-compute-optimal-large-language | 44 |