Irony Identification On Big Bench
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Chinchilla-70B (few-shot, k=5) | 73.0 | Training Compute-Optimal Large Language Models | |
| Gopher-280B (few-shot, k=5) | 69.7 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
0 of 2 row(s) selected.