Standard Suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Natural Language Understanding and Reasoning | Standard Suite Zero-shot (PiQA, ARC-E, ARC-C, HellaSwag, WinoGrande, BoolQ) | PiQA Accuracy (Zero-shot)80.7 | 39 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Natural Language Understanding and Reasoning | Standard Suite Zero-shot (PiQA, ARC-E, ARC-C, HellaSwag, WinoGrande, BoolQ) | PiQA Accuracy (Zero-shot)80.7 | 39 |