BlueBench - Chatbot Abilities — leaderboard
Metric: Score (%). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 97.55 |
| 2 | GPT-4.1 | 96.36 |
| 3 | GPT-4.1 Nano | 95.57 |
| 4 | Mistral Medium 3 | 94.17 |
| 5 | GPT-4o | 94.14 |
| 6 | Mistral Large | 86.13 |
| 7 | Pixtral-12B | 76.54 |
| 8 | Llama 3.3 70B Instruct | 49.69 |
| 9 | O3 Mini | 37.11 |
| 10 | O1 | 34.38 |
| 11 | Llama 3.2 3B Instruct | 25.14 |
| 12 | O4 Mini | 11.39 |
| 13 | Llama 3.2 1B Instruct | 5.7 |
Interactive version: theaggregate.ai/benchmark?slug=bluebench-chatbot-abilities · How the rankings work · Data refreshed daily, snapshot 2026-07-22.