{"benchmark_id":"vibe-eval","name":"Vibe-Eval","parent_benchmark":null,"categories":["multimodal","general","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2405.02287","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.716321+00:00","updated_at":"2026-07-05T18:28:04.564088+00:00","statistics":{"total_models":8,"average_score":0.561875,"min_score":0.409,"max_score":0.672,"score_stddev":0.09340302457629521,"verified_count":0,"self_reported_count":8},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gemini-2.5-pro-preview-06-05","model_name":"Gemini 2.5 Pro Preview 06-05","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.672,"normalized_score":0.672,"verified":false,"self_reported":true,"self_reported_source":"https://blog.google/products/gemini/gemini-2-5-pro-latest-preview/","analysis_method":"Image understanding","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-05","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":2,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.656,"normalized_score":0.656,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/models/gemini/pro/","analysis_method":"Accuracy","verification_date":null,"provider_id":"google","input_cost_per_million":1.25,"output_cost_per_million":10.0,"context_window":1048576,"announcement_date":"2025-05-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.7,"latency_provider":"Google","best_throughput":85.0,"throughput_provider":"Google","context_provider":"Google"},{"rank":3,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.654,"normalized_score":0.654,"verified":false,"self_reported":true,"self_reported_source":"https://developers.googleblog.com/en/start-building-with-gemini-25-flash/","analysis_method":"Accuracy","verification_date":null,"provider_id":"google","input_cost_per_million":0.3,"output_cost_per_million":2.5,"context_window":1048576,"announcement_date":"2025-05-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.7,"latency_provider":"Google","best_throughput":85.0,"throughput_provider":"Google","context_provider":"Google"},{"rank":4,"model_id":"gemini-2.0-flash","model_name":"Gemini 2.0 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.563,"normalized_score":0.563,"verified":false,"self_reported":true,"self_reported_source":"https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/","analysis_method":"Visual understanding in chat models with challenging everyday examples","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-01","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":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.539,"normalized_score":0.539,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/pro/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-01","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":6,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.513,"normalized_score":0.513,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/models/gemini/flash-lite/","analysis_method":"Reka","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-17","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":7,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.489,"normalized_score":0.489,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-01","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":8,"model_id":"gemini-1.5-flash-8b","model_name":"Gemini 1.5 Flash 8B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.409,"normalized_score":0.409,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Visual understanding evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-03-15","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}