Neura Intelligence Index
Back to Leaderboard
HellaSwag
Commonsense natural language inference — predict the most plausible continuation of a scenario
Model Rankings (15)
| # | Model | Score | Provider | Source |
|---|---|---|---|---|
| 1 | 96.4 | OpenAI | ||
| 2 | 96 | Meta | ||
| 3 | 95.4 | Anthropic | ||
| 4 | 95.3 | OpenAI | ||
| 5 | 94.8 | Meta | ||
| 6 | 94.4 | Meta | ||
| 7 | 94 | Alibaba | ||
| 8 | 93.6 | Mistral | ||
| 9 | 93.5 | NVIDIA | ||
| 10 | 91.2 | OpenAI | ||
| 11 | 89 | Anthropic | ||
| 12 | 88.5 | Mistral | ||
| 13 | 86.8 | Microsoft | ||
| 14 | 85.3 | Cohere | ||
| 15 | 82 | Meta |