{"benchmark_id":"cl-bench","benchmark_name":"CL-bench","benchmark_description":"CL-bench is an open-source benchmark with its own data and rubrics for evaluating models on coding and agentic tasks, scored using a setup fully aligned with the official procedure.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":3,"entries":[{"rank":1,"model_id":"hy3","model_name":"Hy3","organization_name":"Tencent","organization_id":"tencent","benchmark_score":0.238,"normalized_score":0.238,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.14,"output_cost_per_million":0.58,"speed_rps":null,"context_window":262144,"release_date":"2026-07-06","announcement_date":"2026-07-06","multimodal":false,"param_count":295000000000,"is_new":false},{"rank":2,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.2048,"normalized_score":0.2048,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.28,"output_cost_per_million":1.1,"speed_rps":null,"context_window":524288,"release_date":"2026-06-01","announcement_date":"2026-06-01","multimodal":true,"param_count":428000000000,"is_new":false},{"rank":3,"model_id":"seed-2.0-mini","model_name":"Seed 2.0 Mini","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.148,"normalized_score":0.148,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":null,"context_window":256000,"release_date":"2026-02-17","announcement_date":"2026-02-17","multimodal":true,"param_count":null,"is_new":false}]}