Metric: Accuracy (higher is better)
| # | Model↕ | Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GAL 120B (zero-shot) | 32.6 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 2 | Chinchilla (few-shot, k=5) | 31.9 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 3 | BLOOM (few-shot, k=5) | 27 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 4 | OPT (few-shot, k=5) | 24.4 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |
| 5 | Gopher (few-shot, k=5) | 23.7 | No | Galactica: A Large Language Model for Science | 2022-11-16 | Code |