BlueBench - Translation — leaderboard
Metric: Score (%). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.3 70B Instruct | 41.71 |
| 2 | GPT-4o | 41.42 |
| 3 | GPT-4.1 | 41.22 |
| 4 | GPT-4.1 Nano | 40.29 |
| 5 | GPT-4.1 Mini | 40.16 |
| 6 | Mistral Large | 39.83 |
| 7 | O3 Mini | 37.79 |
| 8 | O1 | 37.44 |
| 9 | O4 Mini | 33.43 |
| 10 | Pixtral-12B | 32.54 |
| 11 | Llama 3.2 3B Instruct | 31.01 |
| 12 | Llama 3.2 1B Instruct | 23.29 |
| 13 | Mistral Medium 3 | 15.52 |
Interactive version: theaggregate.ai/benchmark?slug=bluebench-translation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.