Mathematical Reasoning on Math Gender (test)
36AccuracyGPT-4o
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-4ocor%_highest_bias_group=Female, inc%_highest_bias_group=Male2025.05 | 36 | 36 | |
| Gemini-Pro-1.5cor%_highest_bias_group=Female, inc%_highest_bias_group=Male2025.05 | 24 | 24 | |
| LLaMA-3-8bcor%_highest_bias_group=Male, inc%_highest_bias_group=Female2025.05 | 18 | 18 | |
| GPT-3.5-turbocor%_highest_bias_group=Female, inc%_highest_bias_group=Male2025.05 | 6 | 6 | |
| Claude-3cor%_highest_bias_group=None, inc%_highest_bias_group=None2025.05 | 0 | 0 |