{"benchmark_id":"chartqa","name":"ChartQA","parent_benchmark":null,"categories":["multimodal","reasoning","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"ChartQA is a large-scale benchmark comprising 9.6K human-written questions and 23.1K questions generated from human-written chart summaries, designed to evaluate models' abilities in visual and logical reasoning over charts.","paper_link":"https://arxiv.org/abs/2203.10244","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.304329+00:00","updated_at":"2026-07-05T18:27:45.050683+00:00","statistics":{"total_models":24,"average_score":0.8421666666666666,"min_score":0.688,"max_score":0.908,"score_stddev":0.053659689887666874,"verified_count":0,"self_reported_count":24},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"claude-3-5-sonnet-20241022","model_name":"Claude 3.5 Sonnet","organization_id":"anthropic","organization_name":"Anthropic","organization_country":"US","score":0.908,"normalized_score":0.908,"verified":false,"self_reported":true,"self_reported_source":"https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf","analysis_method":"test, relaxed accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-10-22","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":"llama-4-maverick","model_name":"Llama 4 Maverick","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.9,"normalized_score":0.9,"verified":false,"self_reported":true,"self_reported_source":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/","analysis_method":"0-shot CoT","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-04-05","param_count":400000000000,"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":"qwen2.5-vl-72b","model_name":"Qwen2.5 VL 72B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.895,"normalized_score":0.895,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-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":72000000000,"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":"nova-pro","model_name":"Nova Pro","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.892,"normalized_score":0.892,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"relaxed accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","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":"llama-4-scout","model_name":"Llama 4 Scout","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.888,"normalized_score":0.888,"verified":false,"self_reported":true,"self_reported_source":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/","analysis_method":"0-shot CoT","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-04-05","param_count":109000000000,"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":"qwen2-vl-72b","model_name":"Qwen2-VL-72B-Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.883,"normalized_score":0.883,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/QwenLM/Qwen2","analysis_method":"score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-29","param_count":73400000000,"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":"pixtral-large","model_name":"Pixtral Large","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.881,"normalized_score":0.881,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/pixtral-large/","analysis_method":"CoT","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-18","param_count":124000000000,"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":"mistral-small-3.2-24b-instruct-2506","model_name":"Mistral Small 3.2 24B Instruct","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.874,"normalized_score":0.874,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","analysis_method":"-","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-20","param_count":23600000000,"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":"qwen2.5-vl-7b","model_name":"Qwen2.5 VL 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.873,"normalized_score":0.873,"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":10,"model_id":"nova-lite","model_name":"Nova Lite","organization_id":"amazon","organization_name":"Amazon","organization_country":"US","score":0.868,"normalized_score":0.868,"verified":false,"self_reported":true,"self_reported_source":"https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card","analysis_method":"relaxed accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-11-20","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":11,"model_id":"deepseek-vl2","model_name":"DeepSeek VL2","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.86,"normalized_score":0.86,"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":12,"model_id":"gpt-4o-2024-08-06","model_name":"GPT-4o","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.857,"normalized_score":0.857,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/hello-gpt-4o/","analysis_method":"test set evaluation","verification_date":null,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":10.0,"context_window":128000,"announcement_date":"2024-08-06","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.5,"latency_provider":"OpenAI","best_throughput":132.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":13,"model_id":"llama-3.2-90b-instruct","model_name":"Llama 3.2 90B Instruct","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.855,"normalized_score":0.855,"verified":false,"self_reported":true,"self_reported_source":"https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/","analysis_method":"-","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-25","param_count":90000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":14,"model_id":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.853,"normalized_score":0.853,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/QwenLM/Qwen2.5-Omni","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-27","param_count":7000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":15,"model_id":"deepseek-vl2-small","model_name":"DeepSeek VL2 Small","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.845,"normalized_score":0.845,"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":16,"model_id":"llama-3.2-11b-instruct","model_name":"Llama 3.2 11B Instruct","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.834,"normalized_score":0.834,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct","analysis_method":"Test, 0-shot CoT relaxed accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-25","param_count":10600000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":17,"model_id":"phi-3.5-vision-instruct","model_name":"Phi-3.5-vision-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.818,"normalized_score":0.818,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-vision-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":"2024-08-23","param_count":4200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":17,"model_id":"pixtral-12b-2409","model_name":"Pixtral-12B","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.818,"normalized_score":0.818,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/pixtral-12b/","analysis_method":"Chain of Thought (CoT)","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-17","param_count":12400000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":19,"model_id":"phi-4-multimodal-instruct","model_name":"Phi-4-multimodal-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.814,"normalized_score":0.814,"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":20,"model_id":"deepseek-vl2-tiny","model_name":"DeepSeek VL2 Tiny","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.81,"normalized_score":0.81,"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":21,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.78,"normalized_score":0.78,"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":22,"model_id":"grok-1.5v","model_name":"Grok-1.5V","organization_id":"xai","organization_name":"xAI","organization_country":"US","score":0.761,"normalized_score":0.761,"verified":false,"self_reported":true,"self_reported_source":"https://x.ai/blog/grok-1.5v","analysis_method":"zero-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-04-12","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":23,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.757,"normalized_score":0.757,"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":24,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.688,"normalized_score":0.688,"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}]}