BlueBench: leaderboard
Metric: Average Score (%). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 64.61 |
| 2 | GPT-4o | 64.13 |
| 3 | GPT-4.1 Mini | 63.01 |
| 4 | Mistral Medium 3 | 60.5 |
| 5 | Llama 3.3 70B Instruct | 58.96 |
| 6 | O1 | 58.6 |
| 7 | GPT-4.1 Nano | 56.98 |
| 8 | Mistral Large | 55.49 |
| 9 | O4 Mini | 53.98 |
| 10 | O3 Mini | 53.85 |
| 11 | Granite 3.3 8B Instruct | 49.29 |
| 12 | Pixtral-12B | 45.38 |
| 13 | Llama 3.2 3B Instruct | 44.27 |
| 14 | Llama 3.2 1B Instruct | 31.83 |
Interactive version: theaggregate.ai/benchmark?slug=bluebench · How It Works · Data refreshed daily, snapshot 2026-09-05.