| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Training Compute-Optimal Large Language Models | ✓ Link | 44 | Chinchilla-70B (few-shot, k=5) | 2022-03-29 |
| PaLM 2 Technical Report | ✓ Link | 42.4 | PaLM-540B (few-shot, k=5) | 2023-05-17 |
| PaLM 2 Technical Report | ✓ Link | 36.5 | PaLM-62B (few-shot, k=5) | 2023-05-17 |
| Scaling Language Models: Methods, Analysis & Insights from Training Gopher | ✓ Link | 35.1 | Gopher-280B (few-shot, k=5) | 2021-12-08 |