LLM Trustworthy - Fairness — leaderboard
Metric: Trust Score (%). Source: huggingface.co. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 7B Chat | 100 |
| 2 | falcon-7B Instruct | 100 |
| 3 | RedPajama-INCITE-7B-Instruct | 100 |
| 4 | mpt-7B-chat | 100 |
| 5 | tulu-2-13B | 97.9 |
| 6 | Claude 2 | 96.81 |
| 7 | zephyr-7B-beta | 95.07 |
| 8 | gemma-7B (IT) | 93.88 |
| 9 | gemma-2B (IT) | 93.02 |
| 10 | vicuna-7B-v1.3 | 85.53 |
| 11 | tulu-2-7B | 83.21 |
| 12 | Llama 3 8B Instruct | 80.05 |
| 13 | Gemini 1.0 Pro | 80.05 |
| 14 | GPT-3.5 Turbo (0301) | 77.57 |
| 15 | GPT-4o Mini (2024-07-18) | 69.74 |
Interactive version: theaggregate.ai/benchmark?slug=llm-trustworthy-fairness · How the rankings work · Data refreshed daily, snapshot 2026-07-22.