LLM Trustworthy - Ethics — leaderboard

Metric: Trust Score (%). Source: huggingface.co. 26 models tracked.

Top models

#ModelScore
1Llama 3 8B Instruct93.74
2Gemini 1.0 Pro93.74
3GPT-4o (2024-05-13)92.02
4GPT-4o Mini (2024-07-18)87.2
5GPT-3.5 Turbo (0301)86.38
6Claude 285.17
7GPT-4 (0314)76.6
8gemma-2B (IT)75.03
9falcon-7B Instruct50.28
10tulu-2-7B49
11vicuna-7B-v1.348.22
12gemma-7B (IT)43.33
13zephyr-7B-beta41.03
14Llama 2 7B Chat40.58
15tulu-2-13B36.64

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