Automated Theorem Proving On Holist Benchmark
Metrics
Percentage correct
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Percentage correct |
|---|---|
| holist-an-environment-for-machine-learning-of | 32.65 |
| learning-to-reason-in-large-theories-without | 36.55 |
| holist-an-environment-for-machine-learning-of | 38.88 |
| graph-representations-for-higher-order-logic | 49.95 |