{"benchmark_id":"acebench","name":"ACEBench","parent_benchmark":null,"categories":["reasoning","finance","general","healthcare","tool_calling"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2501.12851","implementation_link":"https://github.com/ACEBench/ACEBench","verified":false,"created_at":"2026-05-07T16:53:21.382957+00:00","updated_at":"2026-07-05T18:27:41.889898+00:00","statistics":{"total_models":2,"average_score":0.765,"min_score":0.765,"max_score":0.765,"score_stddev":null,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.765,"normalized_score":0.765,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-07-11","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":1,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.765,"normalized_score":0.765,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-05","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}