Evaluation Tasks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Zero-shot Evaluation | Evaluation Tasks Zero-shot Aggregate | Avg. Accuracy79.95 | 74 | |
| Language Modeling | Evaluation Tasks Zero-shot Average | Zero-shot Average Accuracy60.47 | 17 | |
| Path-Following | 10,000 Evaluation Tasks Difficult n=2563 | Path Length Mean (m)0.32 | 3 | |
| Path-Following | 10,000 Evaluation Tasks Medium n=4795 | Mean Path Length (m)0.57 | 3 | |
| Path-Following | 10,000 Evaluation Tasks Easy n=2642 | Path Length Mean (m)0.53 | 3 | |
| Path-Following | Evaluation Tasks n=10000 (All) | Mean Path Length (m)0.45 | 3 |
Showing 6 of 6 rows