List your company

Code Generation on MBPP Sanitized (test)

84.3Pass@1GPT-4o
41.6652.7363.874.87Oct 16, 2024

Evaluation results

MethodLinks
GPT-4oPrompting Method=Personality2024.1084.391.693.9
GPT-4o miniPrompting Method=Personality2024.1082.286.492
Llama 3.1Prompting Method=Personality2024.108185.592.3
GPT-4oPrompting Method=Direct2024.1078.280.182
CodestralPrompting Method=Personality2024.1073.88592.7
Llama 3.1Prompting Method=Direct2024.1069.87476.6
GPT-4o miniPrompting Method=Direct2024.1069.374.777.8
CodestralPrompting Method=Direct2024.1064.273.879.2
CodeLlamaPrompting Method=Personality2024.1046.849.651.2
CodeLlamaPrompting Method=Direct2024.1043.346.647.1