Logical Reasoning On Big Bench Formal
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 |
|---|---|---|---|
| Gopher-280B (few-shot, k=5) | 50.7 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | |
| PaLM 540B (few-shot, k=3) | 53.6 | BloombergGPT: A Large Language Model for Finance | - |
| GPT-NeoX 20B (few-shot, k=3) | 52.8 | BloombergGPT: A Large Language Model for Finance | - |
| OPT 66B (few-shot, k=3) | 54 | BloombergGPT: A Large Language Model for Finance | - |
| PaLM 2 (few-shot, k=3, Direct) | 64.8 | PaLM 2 Technical Report | |
| BLOOM 176B (few-shot, k=3) | 52.8 | BloombergGPT: A Large Language Model for Finance | - |
| Chinchilla-70B (few-shot, k=5) | 52.1 | Training Compute-Optimal Large Language Models | |
| Bloomberg GPT 50B (few-shot, k=3) | 50.8 | BloombergGPT: A Large Language Model for Finance | - |
| PaLM 2 (few-shot, k=3, CoT) | 57.2 | PaLM 2 Technical Report |
0 of 9 row(s) selected.