Neo is leading the MLE Bench with 34.2% score Posted by gauravvij137 on Friday August 15, 2025 @02:47PM from the github.com dept. https://github.com/openai/mle-bench ( 1 comment | on HN )
It can reason, plan and iterate on complex data cleaning, feature engineering and model training tasks.
Neo is now the SOTA Machine Learning Engineering agent on OpenAI's MLE-Bench.