SocialBias-Bench - Pass@Attribute: leaderboard
Metric: Pass@attribute (%; attribute-level correctness of the generated code, using the task's required attributes and leaving out sensitive ones; 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 | Claude 3 Haiku (20240307) | 73.25 |
| 2 | CodeLlama-70B-Instruct-hf | 69.6 |
| 3 | GPT-3.5 Turbo (0125) | 66.6 |
Interactive version: theaggregate.ai/benchmark?slug=socialbias-bench-pass-attribute · How It Works · Data refreshed daily, snapshot 2026-09-26.