{"benchmark_id":"finance-agent","benchmark_name":"Finance Agent","benchmark_description":"Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.","max_score":1.0,"categories":["reasoning","finance","agents"],"modality":"text","total_models":8,"entries":[{"rank":1,"model_id":"claude-opus-4-7","model_name":"Claude Opus 4.7","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.644,"normalized_score":0.644,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-04-16","announcement_date":"2026-04-16","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"claude-sonnet-4-6","model_name":"Claude Sonnet 4.6","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.633,"normalized_score":0.633,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":42.0,"context_window":200000,"release_date":"2026-02-17","announcement_date":"2026-02-17","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"claude-opus-4-6","model_name":"Claude Opus 4.6","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.607,"normalized_score":0.607,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-02-05","announcement_date":"2026-02-05","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"gpt-5.5","model_name":"GPT-5.5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.6,"normalized_score":0.6,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"speed_rps":null,"context_window":1050000,"release_date":"2026-04-23","announcement_date":"2026-04-23","multimodal":true,"param_count":null,"is_new":false},{"rank":5,"model_id":"gemini-3.5-flash","model_name":"Gemini 3.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.579,"normalized_score":0.579,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":1.5,"output_cost_per_million":9.0,"speed_rps":null,"context_window":1048576,"release_date":"2026-05-19","announcement_date":"2026-05-19","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"gpt-5.4","model_name":"GPT-5.4","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.56,"normalized_score":0.56,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":15.0,"speed_rps":50.0,"context_window":1000000,"release_date":"2026-03-05","announcement_date":"2026-03-05","multimodal":true,"param_count":null,"is_new":false},{"rank":7,"model_id":"claude-opus-4-8","model_name":"Claude Opus 4.8","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.539,"normalized_score":0.539,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-05-28","announcement_date":"2026-05-28","multimodal":true,"param_count":null,"is_new":false},{"rank":8,"model_id":"nemotron-3-ultra-550b-a55b","model_name":"Nemotron 3 Ultra (550B A55B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.537,"normalized_score":0.537,"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":"2026-06-04","announcement_date":"2026-06-04","multimodal":false,"param_count":550000000000,"is_new":false}]}