{"benchmark_id":"swe-bench-verified-(agentless)","benchmark_name":"SWE-bench Verified (Agentless)","benchmark_description":"A human-validated subset of SWE-bench that evaluates language models' ability to resolve real-world GitHub issues using an agentless approach. The benchmark tests models on software engineering problems requiring understanding and coordinating changes across multiple functions, classes, and files simultaneously.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.518,"normalized_score":0.518,"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":"2025-07-11","announcement_date":"2025-07-11","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":2,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.357,"normalized_score":0.357,"verified":false,"self_reported":true,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-27","announcement_date":"2026-04-27","multimodal":false,"param_count":1023244718976,"is_new":false}]}