{"benchmark_id":"countbench","name":"CountBench","parent_benchmark":null,"categories":["reasoning","spatial_reasoning","vision"],"modality":"image","multilingual":false,"max_score":100.0,"language":"en","description":"CountBench evaluates object counting capabilities in visual understanding.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.537822+00:00","updated_at":"2026-10-31T18:28:19.835428+00:00","statistics":{"total_models":9,"average_score":11.533,"min_score":0.725,"max_score":96.3,"score_stddev":31.787729051475193,"verified_count":0,"self_reported_count":9},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"seed-1.8","model_name":"Seed 1.8","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":96.3,"normalized_score":0.963,"verified":false,"self_reported":true,"self_reported_source":"https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/research/Seed-1.8-Modelcard.pdf","analysis_method":"Official Table 2; think-high; Pass@1","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.25,"output_cost_per_million":2.0,"context_window":256000,"announcement_date":"2026-02-17","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":2,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.978,"normalized_score":0.978,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.26,"output_cost_per_million":2.6,"context_window":262144,"announcement_date":"2026-02-24","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Novita"},{"rank":2,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.978,"normalized_score":0.978,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.14,"output_cost_per_million":1.0,"context_window":262144,"announcement_date":"2026-02-24","param_count":35000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":2,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.978,"normalized_score":0.978,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-27b","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.32,"output_cost_per_million":3.2,"context_window":262144,"announcement_date":"2026-04-21","param_count":27781427952,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":5,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.976,"normalized_score":0.976,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.5,"output_cost_per_million":3.0,"context_window":1000000,"announcement_date":"2026-04-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":6,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.97,"normalized_score":0.97,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.29,"output_cost_per_million":2.4,"context_window":262144,"announcement_date":"2026-02-24","param_count":122000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":7,"model_id":"seed-2.0-mini","model_name":"Seed 2.0 Mini","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.955,"normalized_score":0.955,"verified":false,"self_reported":true,"self_reported_source":"https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf","analysis_method":"Model Card Table 8 public visual-language benchmarks; Pass@1 percentage score.","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.4,"context_window":256000,"announcement_date":"2026-02-17","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":8,"model_id":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.937,"normalized_score":0.937,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":236000000000,"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":"north-micro-vision-instruct","model_name":"North Micro Vision Instruct","organization_id":"cohere","organization_name":"Cohere","organization_country":"CA","score":0.725,"normalized_score":0.725,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct","analysis_method":"HF model card table (CountBench via VLMEvalKit)","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-08-12","param_count":2400000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}