{"benchmark_id":"bfcl-v4","benchmark_name":"BFCL-V4","benchmark_description":"Berkeley Function Calling Leaderboard V4 (BFCL-V4) evaluates LLMs on their ability to accurately call functions and APIs, including simple, multiple, parallel, and nested function calls across diverse programming scenarios.","max_score":1.0,"categories":["agents","tool_calling"],"modality":"text","total_models":21,"entries":[{"rank":1,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.75,"normalized_score":0.75,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"speed_rps":null,"context_window":1000000,"release_date":"2026-05-19","announcement_date":"2026-05-19","multimodal":false,"param_count":null,"is_new":false},{"rank":2,"model_id":"ling-3.0-flash","model_name":"Ling 3.0 Flash","organization_name":"InclusionAI","organization_id":"inclusionai","benchmark_score":0.73,"normalized_score":0.73,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.06,"output_cost_per_million":0.18,"speed_rps":null,"context_window":131072,"release_date":"2026-08-04","announcement_date":"2026-08-04","multimodal":false,"param_count":124000000000,"is_new":false},{"rank":3,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.729,"normalized_score":0.729,"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":"2026-05-31","announcement_date":"2026-05-31","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"qwen3.5-397b-a17b","model_name":"Qwen3.5-397B-A17B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.729,"normalized_score":0.729,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.45,"output_cost_per_million":3.0,"speed_rps":null,"context_window":262144,"release_date":"2026-02-16","announcement_date":"2026-02-16","multimodal":true,"param_count":397000000000,"is_new":false},{"rank":5,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.722,"normalized_score":0.722,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.29,"output_cost_per_million":2.4,"speed_rps":null,"context_window":262144,"release_date":"2026-02-24","announcement_date":"2026-02-24","multimodal":true,"param_count":122000000000,"is_new":false},{"rank":6,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.685,"normalized_score":0.685,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.26,"output_cost_per_million":2.6,"speed_rps":null,"context_window":262144,"release_date":"2026-02-24","announcement_date":"2026-02-24","multimodal":true,"param_count":27000000000,"is_new":false},{"rank":7,"model_id":"qwen3-max-thinking","model_name":"Qwen3 Max Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.677,"normalized_score":0.677,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":1.2,"output_cost_per_million":6.0,"speed_rps":null,"context_window":256000,"release_date":"2026-02-13","announcement_date":"2026-02-13","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":8,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.673,"normalized_score":0.673,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.14,"output_cost_per_million":1.0,"speed_rps":null,"context_window":262144,"release_date":"2026-02-24","announcement_date":"2026-02-24","multimodal":true,"param_count":35000000000,"is_new":false},{"rank":9,"model_id":"qwen3.5-9b","model_name":"Qwen3.5-9B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.661,"normalized_score":0.661,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.15,"speed_rps":null,"context_window":262144,"release_date":"2026-03-02","announcement_date":"2026-03-02","multimodal":true,"param_count":9000000000,"is_new":false},{"rank":10,"model_id":"nova-2-pro","model_name":"Nova 2 Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.616,"normalized_score":0.616,"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":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false},{"rank":11,"model_id":"granite-4.2-30b","model_name":"IBM Granite 4.2 30B","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.6139,"normalized_score":0.6139,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.16,"output_cost_per_million":0.65,"speed_rps":null,"context_window":131072,"release_date":"2026-08-25","announcement_date":"2026-08-25","multimodal":false,"param_count":30000000000,"is_new":false},{"rank":12,"model_id":"nova-2-lite","model_name":"Nova 2 Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.603,"normalized_score":0.603,"verified":false,"self_reported":true,"provider_id":"bedrock","input_cost_per_million":0.3,"output_cost_per_million":2.5,"speed_rps":null,"context_window":1000000,"release_date":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"nova-2-omni","model_name":"Nova 2 Omni","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.583,"normalized_score":0.583,"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":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false},{"rank":14,"model_id":"seed-1.8","model_name":"Seed 1.8","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.572,"normalized_score":0.572,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.25,"output_cost_per_million":2.0,"speed_rps":null,"context_window":256000,"release_date":"2026-02-17","announcement_date":"2026-02-17","multimodal":true,"param_count":null,"is_new":false},{"rank":15,"model_id":"lfm-2.5-2.6b","model_name":"LFM2.5-2.6B","organization_name":"Liquid AI","organization_id":"liquid","benchmark_score":0.5688,"normalized_score":0.5688,"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":"2026-08-04","announcement_date":"2026-08-04","multimodal":false,"param_count":2690000000,"is_new":false},{"rank":16,"model_id":"granite-4.2-3b","model_name":"IBM Granite 4.2 3B","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.5241,"normalized_score":0.5241,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.03,"output_cost_per_million":0.12,"speed_rps":null,"context_window":131072,"release_date":"2026-08-25","announcement_date":"2026-08-25","multimodal":false,"param_count":3000000000,"is_new":false},{"rank":17,"model_id":"granite-4.2-8b","model_name":"IBM Granite 4.2 8B","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.5239,"normalized_score":0.5239,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.06,"output_cost_per_million":0.25,"speed_rps":null,"context_window":131072,"release_date":"2026-08-25","announcement_date":"2026-08-25","multimodal":false,"param_count":8000000000,"is_new":false},{"rank":18,"model_id":"qwen3.5-4b","model_name":"Qwen3.5-4B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.503,"normalized_score":0.503,"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":"2026-03-02","announcement_date":"2026-03-02","multimodal":true,"param_count":4000000000,"is_new":false},{"rank":19,"model_id":"qwen3.5-2b","model_name":"Qwen3.5-2B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.436,"normalized_score":0.436,"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":"2026-03-02","announcement_date":"2026-03-02","multimodal":true,"param_count":2000000000,"is_new":false},{"rank":20,"model_id":"lfm-2.5-vl-3b","model_name":"LFM2.5-VL-3B","organization_name":"Liquid AI","organization_id":"liquid","benchmark_score":0.325,"normalized_score":0.325,"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":"2026-08-12","announcement_date":"2026-08-12","multimodal":true,"param_count":3123483888,"is_new":false},{"rank":21,"model_id":"qwen3.5-0.8b","model_name":"Qwen3.5-0.8B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.253,"normalized_score":0.253,"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":"2026-03-02","announcement_date":"2026-03-02","multimodal":true,"param_count":800000000,"is_new":false}]}