{"benchmark_id":"livecodebench-v5","benchmark_name":"LiveCodeBench v5","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":9,"entries":[{"rank":1,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.756,"normalized_score":0.756,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":85.0,"context_window":1048576,"release_date":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.639,"normalized_score":0.639,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"qwen3-vl-235b-a22b-instruct","model_name":"Qwen3 VL 235B A22B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.614,"normalized_score":0.614,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":236000000000,"is_new":false},{"rank":4,"model_id":"minicpm-sala","model_name":"MiniCPM-SALA","organization_name":"OpenBMB","organization_id":"openbmb","benchmark_score":0.6048,"normalized_score":0.6048,"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":"2026-02-11","announcement_date":"2026-02-11","multimodal":false,"param_count":9477203968,"is_new":false},{"rank":5,"model_id":"gemini-2.0-flash-lite","model_name":"Gemini 2.0 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.289,"normalized_score":0.289,"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":"2025-02-05","announcement_date":"2025-02-05","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.257,"normalized_score":0.257,"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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":7,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_name":"Google","organization_id":"google","benchmark_score":0.257,"normalized_score":0.257,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false},{"rank":8,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.186,"normalized_score":0.186,"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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":9,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_name":"Google","organization_id":"google","benchmark_score":0.186,"normalized_score":0.186,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false}]}