{"benchmark_id":"kimi-code-bench-v2","benchmark_name":"Kimi Code Bench v2","benchmark_description":"Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"kimi-k3","model_name":"Kimi K3","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.729,"normalized_score":0.729,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-16","announcement_date":"2026-07-16","multimodal":true,"param_count":2800000000000,"is_new":false},{"rank":2,"model_id":"kimi-k2.7-code","model_name":"Kimi K2.7 Code","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.62,"normalized_score":0.62,"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":"2026-06-12","announcement_date":"2026-06-12","multimodal":true,"param_count":1000000000000,"is_new":false}]}