{"benchmark_id":"humaneval-er","benchmark_name":"HumanEval-ER","benchmark_description":"A variant of the HumanEval benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics","max_score":1.0,"categories":["reasoning"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.811,"normalized_score":0.811,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-07-11","announcement_date":"2025-07-11","multimodal":false,"param_count":1000000000000,"is_new":false}]}