# HellaSwag — AI model rankings

commonsense completion of short scenarios

9 tracked models have a published HellaSwag score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-4 | OpenAI | 95.3% | Lab | Mar 14 2023 |
| 2 | Gemini 1.5 Pro | Google | 92.5% | Lab | Feb 15 2024 |
| 3 | Gemini 1.0 Ultra | Google | 87.8% | Lab | Feb 8 2024 |
| 4 | Gemini 1.5 Flash | Google | 86.5% | Lab | May 14 2024 |
| 5 | Gemma 2 | Google | 86.4% | Lab | Jun 27 2024 |
| 6 | LLaMA 2 | Meta | 85.3% | Lab | Jul 18 2023 |
| 7 | Gemini 1.0 Pro | Google | 84.7% | Lab | Dec 13 2023 |
| 8 | LLaMA 1 | Meta | 84.2% | Lab | Feb 24 2023 |
| 9 | Gemma 1 | Google | 81.2% | Lab | Feb 21 2024 |


---

Canonical page: https://aireleasetracker.com/benchmark/hellaswag
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.