{"benchmark_id":"vibe-eval","benchmark_name":"Vibe-Eval","benchmark_description":"VIBE-Eval is a hard evaluation suite for measuring progress of multimodal language models, consisting of 269 visual understanding prompts with gold-standard responses authored by experts. The benchmark has dual objectives: vibe checking multimodal chat models for day-to-day tasks and rigorously testing frontier models, with the hard set containing >50% questions that all frontier models answer incorrectly.","max_score":1.0,"categories":["multimodal","general","vision"],"modality":"multimodal","total_models":8,"entries":[{"rank":1,"model_id":"gemini-2.5-pro-preview-06-05","model_name":"Gemini 2.5 Pro Preview 06-05","organization_name":"Google","organization_id":"google","benchmark_score":0.672,"normalized_score":0.672,"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":"2025-06-05","announcement_date":"2025-06-05","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.656,"normalized_score":0.656,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":85.0,"context_window":1048576,"release_date":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.654,"normalized_score":0.654,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"gemini-2.0-flash","model_name":"Gemini 2.0 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.563,"normalized_score":0.563,"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":"2024-12-01","announcement_date":"2024-12-01","multimodal":true,"param_count":null,"is_new":false},{"rank":5,"model_id":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.539,"normalized_score":0.539,"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":"2024-05-01","announcement_date":"2024-05-01","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.513,"normalized_score":0.513,"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":"2025-06-17","announcement_date":"2025-06-17","multimodal":true,"param_count":null,"is_new":false},{"rank":7,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.489,"normalized_score":0.489,"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":"2024-05-01","announcement_date":"2024-05-01","multimodal":true,"param_count":null,"is_new":false},{"rank":8,"model_id":"gemini-1.5-flash-8b","model_name":"Gemini 1.5 Flash 8B","organization_name":"Google","organization_id":"google","benchmark_score":0.409,"normalized_score":0.409,"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":"2024-03-15","announcement_date":"2024-03-15","multimodal":true,"param_count":8000000000,"is_new":false}]}