{"benchmark_id":"complexfuncbench","name":"ComplexFuncBench","parent_benchmark":null,"categories":["reasoning","structured_output","long_context","tool_calling"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"ComplexFuncBench is a benchmark designed to evaluate large language models' capabilities in handling complex function calling scenarios. It encompasses multi-step and constrained function calling tasks that require long-parameter filling, parameter value reasoning, and managing contexts up to 128k tokens. The benchmark includes 1,000 samples across five real-world scenarios.","paper_link":"https://arxiv.org/abs/2501.10132","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.503592+00:00","updated_at":"2026-07-05T18:27:45.748609+00:00","statistics":{"total_models":7,"average_score":0.4754285714285715,"min_score":0.057,"max_score":0.665,"score_stddev":0.2543952680003156,"verified_count":0,"self_reported_count":7},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gpt-4o-2024-08-06","model_name":"GPT-4o","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.665,"normalized_score":0.665,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-4-1/","analysis_method":"Accuracy","verification_date":null,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":10.0,"context_window":128000,"announcement_date":"2024-08-06","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.5,"latency_provider":"OpenAI","best_throughput":132.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":2,"model_id":"gpt-4.1-2025-04-14","model_name":"GPT-4.1","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.655,"normalized_score":0.655,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"Standard benchmark","verification_date":null,"provider_id":"openai","input_cost_per_million":2.0,"output_cost_per_million":8.0,"context_window":1047576,"announcement_date":"2025-04-14","param_count":null,"is_open_source":false,"is_new":false,"best_latency":10.0,"latency_provider":"OpenAI","best_throughput":100.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":3,"model_id":"nova-2-sonic","model_name":"Nova 2 Sonic","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.652,"normalized_score":0.652,"verified":false,"self_reported":true,"self_reported_source":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","analysis_method":"accuracy (via TTS)","verification_date":null,"provider_id":"bedrock","input_cost_per_million":0.33,"output_cost_per_million":2.75,"context_window":1000000,"announcement_date":"2025-12-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Bedrock","best_throughput":null,"throughput_provider":"Bedrock","context_provider":"Bedrock"},{"rank":4,"model_id":"gpt-4.5","model_name":"GPT-4.5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.63,"normalized_score":0.63,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-4-1/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-27","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"gpt-4.1-mini-2025-04-14","model_name":"GPT-4.1 mini","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.493,"normalized_score":0.493,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"Standard benchmark","verification_date":null,"provider_id":"openai","input_cost_per_million":0.4,"output_cost_per_million":1.6,"context_window":1047576,"announcement_date":"2025-04-14","param_count":null,"is_open_source":false,"is_new":false,"best_latency":5.0,"latency_provider":"OpenAI","best_throughput":150.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":6,"model_id":"o3-mini","model_name":"o3-mini","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.176,"normalized_score":0.176,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-4-1/","analysis_method":"benchmark score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-30","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":7,"model_id":"gpt-4.1-nano-2025-04-14","model_name":"GPT-4.1 nano","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.057,"normalized_score":0.057,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-4-1/","analysis_method":"Standard benchmark","verification_date":null,"provider_id":"openai","input_cost_per_million":0.1,"output_cost_per_million":0.4,"context_window":1047576,"announcement_date":"2025-04-14","param_count":null,"is_open_source":false,"is_new":false,"best_latency":2.0,"latency_provider":"OpenAI","best_throughput":200.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"}]}