# ARC-Challenge — AI model rankings

multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI

6 tracked models have a published ARC-Challenge 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 | LLaMA 3.1 | Meta | 96.9% | Lab | Jul 23 2024 |
| 2 | GPT-4 | OpenAI | 96.3% | Lab | Mar 14 2023 |
| 3 | Gemma 2 | Google | 71.4% | Lab | Jun 27 2024 |
| 4 | LLaMA 2 | Meta | 57.4% | Lab | Jul 18 2023 |
| 5 | LLaMA 1 | Meta | 56% | Lab | Feb 24 2023 |
| 6 | Gemma 1 | Google | 53.2% | Lab | Feb 21 2024 |


---

Canonical page: https://aireleasetracker.com/benchmark/arc-challenge
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.