{"benchmark_id":"livecodebench-v5-24.12-25.2","benchmark_name":"LiveCodeBench v5 24.12-25.2","benchmark_description":"LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"kimi-k1.5","model_name":"Kimi-k1.5","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.625,"normalized_score":0.625,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":true,"param_count":null,"is_new":false}]}