{"benchmark_id":"researchclawbench","benchmark_name":"ResearchClawBench","benchmark_description":"ResearchClawBench evaluates research agents on realistic, tool-using research tasks that require code execution and filesystem workspace interaction.","max_score":1.0,"categories":["research","agents","tool_calling"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"mimo-v2.5","model_name":"MiMo-V2.5","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.1691,"normalized_score":0.1691,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.168,"output_cost_per_million":0.336,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-22","announcement_date":"2026-04-22","multimodal":true,"param_count":310775040000,"is_new":false}]}