SocialBias-Bench: leaderboard
Metric: Code bias score (%; share of executable generated snippets whose output changes when any one sensitive attribute changes; 343 human-centred coding tasks, five completions each at temperature 1.0). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | CodeLlama-70B-Instruct-hf | 28.34 |
| 2 | Claude 3 Haiku (20240307) | 36.33 |
| 3 | GPT-3.5 Turbo (0125) | 60.58 |
Interactive version: theaggregate.ai/benchmark?slug=socialbias-bench · How It Works · Data refreshed daily, snapshot 2026-09-26.