BlueBench - News Classification: leaderboard
Metric: Score (%). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 69.07 |
| 2 | O1 | 68.16 |
| 3 | O4 Mini | 67.37 |
| 4 | GPT-4.1 Mini | 66.67 |
| 5 | GPT-4.1 | 66.29 |
| 6 | Llama 3.3 70B Instruct | 59.89 |
| 7 | Mistral Medium 3 | 53.76 |
| 8 | Granite 3.3 8B Instruct | 46.07 |
| 9 | O3 Mini | 43.06 |
| 10 | GPT-4.1 Nano | 42.16 |
| 11 | Llama 3.2 3B Instruct | 36.47 |
| 12 | Mistral Large | 29.01 |
| 13 | Pixtral-12B | 21.54 |
| 14 | Llama 3.2 1B Instruct | 20 |
Interactive version: theaggregate.ai/benchmark?slug=bluebench-news-classification · How It Works · Data refreshed daily, snapshot 2026-09-05.