Metric: Accuracy (higher is better)
| # | Model↕ | Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Chinchilla-70B (few-shot, k=5) | 69.1 | No | Training Compute-Optimal Large Language Models | 2022-03-29 | Code |
| 2 | Gopher-280B (few-shot, k=5) | 56.4 | No | Scaling Language Models: Methods, Analysis & Ins... | 2021-12-08 | Code |
| 3 | OPT 175B | 49.1 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 4 | GAL 120B (few-shot, k=5) | 48.7 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 5 | GAL 30B (few-shot, k=5) | 47 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 6 | BLOOM 176B | 1.3 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |