A benchmark of roughly 70,000 multiple-choice questions designed to evaluate commonsense reasoning.
Browse the latest scores, model modes, release dates, and parameter sizes for HellaSwag.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Claude3-Opus Standard Mode | 95.40 | 2024-03-04 | Unknown | Closed | |
 Gemma2-27B Standard Mode | 86.40 | 2024-05-14 | 27B | Free Commercial | |
Gemma 3 - 27B (IT) Standard Mode | 85.60 | 2025-03-12 | 27B | Free Commercial |
