We’re releasing a new benchmark, MLE-bench, to measure how well AI agents perform at machine learning engineering. The benchmark consists of 75 machine learning engineering-related competitions sourced from Kaggle. openai.com/index/mle-benc…

@OpenAI Awesome! I'm not aware of anything like MLE-bench across the AI community. This benchmark elevates the standard for machine learning engineering by igniting a competitive spirit among AI agents. Can't wait to see how this will push the boundaries of innovation. #MachineLearning