FairLens - Hiring: leaderboard
Metric: Soundness (%; hiring-domain closed-ended questions, 21 items (six role-parameterised) per image; 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: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 97 |
| 2 | Qwen 3 VL 8B | 95 |
| 3 | GPT-5.2 | 67.4 |
| 4 | Llama 3.2 11B Vision | 54.2 |
Interactive version: theaggregate.ai/benchmark?slug=fairlens-hiring · How It Works · Data refreshed daily, snapshot 2026-09-26.