BlueBench - Product Help — leaderboard

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

Top models

#ModelScore
1Llama 3.3 70B Instruct86.64
2O3 Mini86.08
3GPT-4o85.95
4GPT-4.1 Mini84.95
5O4 Mini84.27
6O183
7GPT-4.182.33
8Mistral Medium 379.65
9Llama 3.2 3B Instruct75.58
10GPT-4.1 Nano68.52
11Mistral Large67.02
12Pixtral-12B59.87
13Llama 3.2 1B Instruct45.62

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