| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | Llama-2 13B (on 100 first questions, 4-shot, auto-optimized prompting) | – | Accuracy: 43Parameters (Billion): 13 |
| arithmetic-reasoning-on-gsm8k | Llama-2 70B (on 100 first questions, 4-shot, auto-optimized prompting) | – | Accuracy: 61Parameters (Billion): 70 |
| arithmetic-reasoning-on-gsm8k | Mistral 7B (on 100 first questions, 4-shot, auto-optimized prompting) | – | Accuracy: 41Parameters (Billion): 7 |