CRASS
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Counterfactual Reasoning | CRASS | Exact Match Performance94.53 | 11 | |
| Causal Variable Identification | CRASS | F1 (X)92.3 | 7 | |
| Outcome Reasoning | CRASS | M' (F1 Mean)92.1 | 7 | |
| Logic-heavy Reasoning | CRASS | Score56.22 | 6 |
Showing 4 of 4 rows