Logical Reasoning on BIG-bench (Logic Grid Puzzle)
Metric: Accuracy (higher is better)
Metric: Accuracy (higher is better)
| # | Model↕ | Accuracy▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Chinchilla-70B (few-shot, k=5) | 44 | No | Training Compute-Optimal Large Language Models | 2022-03-29 | Code |
| 2 | PaLM-540B (few-shot, k=5) | 42.4 | No | PaLM 2 Technical Report | 2023-05-17 | Code |
| 3 | PaLM-62B (few-shot, k=5) | 36.5 | No | PaLM 2 Technical Report | 2023-05-17 | Code |
| 4 | Gopher-280B (few-shot, k=5) | 35.1 | No | Scaling Language Models: Methods, Analysis & Ins... | 2021-12-08 | Code |