{"benchmark_id":"infovqa","name":"InfoVQA","parent_benchmark":null,"categories":["multimodal","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"InfoVQA dataset with 30,000 questions and 5,000 infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills","paper_link":"https://arxiv.org/abs/2104.12756","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.010026+00:00","updated_at":"2026-07-05T18:27:50.610841+00:00","statistics":{"total_models":9,"average_score":0.7157777777777777,"min_score":0.5,"max_score":0.834,"score_stddev":0.1039251867664641,"verified_count":0,"self_reported_count":9},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen2.5-vl-32b","model_name":"Qwen2.5 VL 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.834,"normalized_score":0.834,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-28","param_count":33500000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"qwen2.5-vl-7b","model_name":"Qwen2.5 VL 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.826,"normalized_score":0.826,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-26","param_count":8290000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"deepseek-vl2","model_name":"DeepSeek VL2","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.781,"normalized_score":0.781,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/pdf/2412.10302","analysis_method":"test","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-13","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"deepseek-vl2-small","model_name":"DeepSeek VL2 Small","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.758,"normalized_score":0.758,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/pdf/2412.10302","analysis_method":"test","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-13","param_count":16000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"phi-4-multimodal-instruct","model_name":"Phi-4-multimodal-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.727,"normalized_score":0.727,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct","analysis_method":"Standard Evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-01","param_count":5600000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.706,"normalized_score":0.706,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"multimodal evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":27000000000,"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":"deepseek-vl2-tiny","model_name":"DeepSeek VL2 Tiny","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.661,"normalized_score":0.661,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/pdf/2412.10302","analysis_method":"test","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-13","param_count":3000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.649,"normalized_score":0.649,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"multimodal evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":12000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":9,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.5,"normalized_score":0.5,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"multimodal evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}