{"benchmark_id":"livecodebench(01-09)","benchmark_name":"LiveCodeBench(01-09)","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":"deepseek-v2.5","model_name":"DeepSeek-V2.5","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.418,"normalized_score":0.418,"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":"2024-05-08","announcement_date":"2024-05-08","multimodal":false,"param_count":236000000000,"is_new":false}]}