# SimpleQA — AI model rankings

accuracy on short, fact-seeking questions in the original SimpleQA set

15 tracked models have a published SimpleQA 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-4.5 | OpenAI | 62.5% | Lab | Feb 27 2025 |
| 2 | Gemini 2.5 Pro | Google | 52.9% | Lab | Mar 25 2025 |
| 3 | o3 | OpenAI | 49.4% | Lab | Apr 16 2025 |
| 4 | Gemini 2.0 Pro | Google | 44.3% | Lab | Feb 5 2025 |
| 5 | GPT-4.1 | OpenAI | 41.6% | Lab | Apr 14 2025 |
| 6 | Gemini 2.5 Flash | Google | 29.7% | Lab | Apr 17 2025 |
| 7 | Gemini 2.0 Flash-Lite | Google | 21.7% | Lab | Feb 5 2025 |
| 8 | o4-mini | OpenAI | 20.2% | Lab | Apr 16 2025 |
| 9 | o4-mini-high | OpenAI | 19.3% | Lab | Apr 16 2025 |
| 10 | GPT-4.1 mini | OpenAI | 16.8% | Lab | Apr 14 2025 |
| 11 | o3-mini-high | OpenAI | 13.8% | Lab | Jan 31 2025 |
| 12 | o3-mini | OpenAI | 13.4% | Lab | Jan 31 2025 |
| 13 | Gemini 2.5 Flash-Lite | Google | 10.7% | Lab | Jun 17 2025 |
| 14 | Gemma 3 | Google | 10% | Lab | Mar 12 2025 |
| 15 | GPT-4.1 nano | OpenAI | 7.6% | Lab | Apr 14 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/simpleqa
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.