FairLens: leaderboard

Metric: Soundness (%; share of closed-ended answers matching the sound answer, averaged over the hiring, legal and healthcare domains; 1,505 UTKFace portraits (adults 25-65, stratified by gender, race and age) paired with multiple-choice questions; the sound answer follows the evidence stated in the question, or is Cannot tell when the face alone is insufficient; greedy decoding). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1Qwen 2.5 VL 7B Instruct85.7
2GPT-5.277.1
3Qwen 3 VL 8B65.8
4Llama 3.2 11B Vision21.9

Interactive version: theaggregate.ai/benchmark?slug=fairlens · How It Works · Data refreshed daily, snapshot 2026-09-26.