SuperGLUE
General QA · 2019-05-02
A suite of diverse language understanding tasks designed to be more challenging than GLUE, emphasizing reasoning and sample efficiency.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-3 175B | 58.2 |
| GPT-3 13B | 54.4 |
| GPT-3 6.7B | 52.3 |
| GPT-3 2.7B | 50.1 |
| GPT-3 XL | 49.6 |
| GPT-3 Medium | 47.4 |
| GPT-3 Large | 46.8 |
| GPT-3 Small | 40.6 |