Code Generation on Coding Gender (test)
40Cor (%)GPT-4o
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-4ocor%_highest_bias_group=Female, inc%_highest_bias_group=Male2025.05 | 40 | 40 | |
| Gemini-Pro-1.5cor%_highest_bias_group=Female, inc%_highest_bias_group=Male2025.05 | 14 | 14 | |
| GPT-3.5-turbocor%_highest_bias_group=Female, inc%_highest_bias_group=Male2025.05 | 4 | 4 | |
| Claude-3cor%_highest_bias_group=Male, inc%_highest_bias_group=Female2025.05 | 4 | 4 | |
| LLaMA-3-8bcor%_highest_bias_group=Male, inc%_highest_bias_group=Female2025.05 | 4 | 4 |