Logical Reasoning On Big Bench Strategyqa
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
| Paper Title | Repository | ||
|---|---|---|---|
| PaLM-540B (few-shot, k=5) | 73.9 | PaLM: Scaling Language Modeling with Pathways | |
| Chinchilla-70B (few-shot, k=5) | 68.3 | Training Compute-Optimal Large Language Models | |
| PaLM-62B (few-shot, k=5) | 65.4 | PaLM: Scaling Language Modeling with Pathways | |
| Gopher-280B (few-shot, k=5) | 61.0 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
0 of 4 row(s) selected.