Neura Intelligence Index
Back to Leaderboard
GSM8K
Grade School Math — 8,500 linguistically diverse grade school math word problems
Model Rankings (19)
| # | Model | Score | Provider | Source |
|---|---|---|---|---|
| 1 | 97.8 | Anthropic | ||
| 2 | 97.8 | OpenAI | ||
| 3 | 97.2 | Anthropic | ||
| 4 | 96.8 | Meta | ||
| 5 | 96.4 | Anthropic | ||
| 6 | 95.8 | Alibaba | ||
| 7 | 95.8 | OpenAI | ||
| 8 | 95.8 | Meta | ||
| 9 | 95.1 | Meta | ||
| 10 | 95 | Anthropic | ||
| 11 | 94.8 | OpenAI | ||
| 12 | 93.2 | OpenAI | ||
| 13 | 93.1 | Mistral | ||
| 14 | 92.4 | Anthropic | ||
| 15 | 92.3 | NVIDIA | ||
| 16 | 90.5 | Mistral | ||
| 17 | 89.1 | Microsoft | ||
| 18 | 87.5 | Cohere | ||
| 19 | 84.5 | Meta |