TinyGSM: achieving >80% on GSM8k with small language models

Open paper
Benchmark Model Rank Results
arithmetic-reasoning-on-gsm8kPhi-GSM 2.7B (fine-tuned)–Accuracy: 74.3Parameters (Billion): 2.7
arithmetic-reasoning-on-gsm8kPhi-GSM+V 1.3B+1.3B (verify48@1)–Accuracy: 81.5Parameters (Billion): 2.6

Rank counts only results with a code link.