General Linguistic Evaluation on Linguistic Scenarios All Tasks
63.4Average AccuracyGPT-3
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-3Evaluation Protocol=1-shot2023.03 | 63.4 | — | |
| BloombergGPTEvaluation Protocol=1-shot2023.03 | 60.63 | 85 | |
| OPT-66BEvaluation Protocol=1-shot2023.03 | 58.59 | 58 | |
| BLOOM-176BEvaluation Protocol=1-shot2023.03 | 58.26 | 42 | |
| GPT-NeoXEvaluation Protocol=1-shot2023.03 | 57.18 | 27 |