# DROP — AI model rankings

three-shot token F1 on questions requiring reasoning over paragraphs

15 tracked models have a published DROP 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 | o1-mini | OpenAI | 83.9 | Lab | Sep 12 2024 |
| 2 | GPT-4o | OpenAI | 83.7 | Lab | May 13 2024 |
| 3 | GPT-4.5 | OpenAI | 83.4 | Lab | Feb 27 2025 |
| 4 | GPT-4 Turbo | OpenAI | 83.2 | Lab | Nov 6 2023 |
| 5 | GPT-4.1 nano | OpenAI | 82.2 | Lab | Apr 14 2025 |
| 6 | GPT-4.1 mini | OpenAI | 81 | Lab | Apr 14 2025 |
| 7 | GPT-4 | OpenAI | 80.9 | Lab | Mar 14 2023 |
| 8 | o3-mini-high | OpenAI | 80.6 | Lab | Jan 31 2025 |
| 8 | o3 | OpenAI | 80.6 | Lab | Apr 16 2025 |
| 10 | GPT-4o mini | OpenAI | 79.7 | Lab | Jul 18 2024 |
| 11 | GPT-4.1 | OpenAI | 79.4 | Lab | Apr 14 2025 |
| 12 | o3-mini | OpenAI | 79.2 | Lab | Jan 31 2025 |
| 13 | o4-mini-high | OpenAI | 78.1 | Lab | Apr 16 2025 |
| 14 | o4-mini | OpenAI | 77.7 | Lab | Apr 16 2025 |
| 15 | o1-preview | OpenAI | 74.8 | Lab | Sep 12 2024 |


---

Canonical page: https://aireleasetracker.com/benchmark/drop-f1-3shot
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.
