{"benchmark_id":"mle-bench-lite","benchmark_name":"MLE-Bench Lite","benchmark_description":"MLE-Bench Lite evaluates AI agents on machine learning engineering tasks, testing their ability to build, train, and optimize ML models for Kaggle-style competitions in a lightweight evaluation format.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.666,"normalized_score":0.666,"verified":false,"self_reported":true,"provider_id":"fireworks","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":196608,"release_date":"2026-03-18","announcement_date":"2026-03-18","multimodal":false,"param_count":null,"is_new":false}]}