BlueBench - Chatbot Abilities — leaderboard

Metric: Score (%). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1GPT-4.1 Mini97.55
2GPT-4.196.36
3GPT-4.1 Nano95.57
4Mistral Medium 394.17
5GPT-4o94.14
6Mistral Large86.13
7Pixtral-12B76.54
8Llama 3.3 70B Instruct49.69
9O3 Mini37.11
10O134.38
11Llama 3.2 3B Instruct25.14
12O4 Mini11.39
13Llama 3.2 1B Instruct5.7

Interactive version: theaggregate.ai/benchmark?slug=bluebench-chatbot-abilities · How the rankings work · Data refreshed daily, snapshot 2026-07-22.