{"benchmark_id":"acebench","benchmark_name":"ACEBench","benchmark_description":"ACEBench is a comprehensive benchmark for evaluating Large Language Models' tool usage capabilities across three primary evaluation types: Normal (basic tool usage scenarios), Special (tool usage with ambiguous or incomplete instructions), and Agent (multi-agent interactions simulating real-world dialogues). The benchmark covers 4,538 APIs across 8 major domains and 68 sub-domains including technology, finance, entertainment, society, health, culture, and environment, supporting both English and Chinese languages.","max_score":1.0,"categories":["reasoning","finance","general","healthcare","tool_calling"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.765,"normalized_score":0.765,"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":"2025-09-05","announcement_date":"2025-09-05","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":2,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.765,"normalized_score":0.765,"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}]}