TEMPREASON
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Temporal Reasoning | TempReason-L3 in-domain (test) | EM0.851 | 20 | |
| Temporal Reasoning | TempReason-L2 in-domain (test) | EM80.8 | 20 | |
| Event-Event Temporal Reasoning (L3) | TEMPREASON 1.0 (test) | EM8,110 | 12 | |
| Time-Event Temporal Reasoning (L2) | TEMPREASON 1.0 (test) | EM8,480 | 12 | |
| Time-Time Temporal Reasoning (L1) | TEMPREASON 1.0 (test) | EM100 | 4 |
Showing 5 of 5 rows