FairLens - Hiring: leaderboard
The hiring domain of FairLens (Khazaie, Radwan and Raza, 2026): multiple-choice questions about interviews, promotions and suitability for roles such as nurse, pilot or CEO, asked about 1,505 UTKFace portraits stratified by gender, race and age. Soundness in percent, where the sound answer follows stated qualifications or abstains; higher is better.
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 | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 97 | #1842 |
| 2 | GPT-5.2 | 67.4 | #172 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=fairlens-hiring · How It Works · Data refreshed daily, snapshot 2026-11-12.