aiXamine - Fairness & Bias: leaderboard

Metric: Service score (0-100; normalized pass rate). Source: arxiv.org. 42 models tracked.

Top models

#ModelScore
1Gemma 4 31B79
2Gemma 4 26B A4B77.5
3Gemini 3 Flash (Preview)76.7
4GPT-OSS-120B72.9
5Phi-472
6Qwen 3.5 27B71.2
7GPT-5 Mini68.8
8GPT-OSS-20B67.6
9GPT-4o67.5
10Gemini 2.0 Flash (001)66.9
11Gemma 4 E4B65.8
12Llama 3.1 8B65.7
13Gemma 2 27B64.7
14Qwen 3.5 122B A10B64.3
15DeepSeek R1 Distill Qwen 14B64

Interactive version: theaggregate.ai/benchmark?slug=aixamine-fairness-bias · How It Works · Data refreshed daily, snapshot 2026-09-19.