{"benchmark_id":"odinw","name":"ODinW","parent_benchmark":null,"categories":["vision"],"modality":"image","multilingual":false,"max_score":1.0,"language":"en","description":"Object Detection in the Wild (ODinW) benchmark for evaluating object detection models' task-level transfer ability across diverse real-world datasets in terms of prediction accuracy and adaptation efficiency","paper_link":"https://arxiv.org/abs/2112.03857","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.487564+00:00","updated_at":"2026-07-05T18:27:57.420665+00:00","statistics":{"total_models":16,"average_score":0.452875,"min_score":0.394,"max_score":0.518,"score_stddev":0.040396163184144115,"verified_count":0,"self_reported_count":16},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.518,"normalized_score":0.518,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6","analysis_method":"13 datasets","verification_date":null,"provider_id":"together","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":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":2,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.511,"normalized_score":0.511,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7-plus","analysis_method":"13 datasets","verification_date":null,"provider_id":"together","input_cost_per_million":0.32,"output_cost_per_million":1.28,"context_window":1000000,"announcement_date":"2026-05-31","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":3,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.508,"normalized_score":0.508,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":"13","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-16","param_count":35000000000,"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":"qwen3-vl-235b-a22b-instruct","model_name":"Qwen3 VL 235B A22B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.486,"normalized_score":0.486,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","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":5,"model_id":"qwen3-vl-4b-instruct","model_name":"Qwen3 VL 4B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.482,"normalized_score":0.482,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.6,"context_window":262144,"announcement_date":"2025-09-22","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":6,"model_id":"qwen3-vl-30b-a3b-instruct","model_name":"Qwen3 VL 30B A3B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.475,"normalized_score":0.475,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","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":31000000000,"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":"qwen3-vl-32b-instruct","model_name":"Qwen3 VL 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.466,"normalized_score":0.466,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","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":33000000000,"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":"qwen3-vl-8b-instruct","model_name":"Qwen3 VL 8B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.447,"normalized_score":0.447,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","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":9000000000,"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":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.445,"normalized_score":0.445,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"13","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":122000000000,"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":"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":0.432,"normalized_score":0.432,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","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":11,"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":0.426,"normalized_score":0.426,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"13","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":35000000000,"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":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.424,"normalized_score":0.424,"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":13,"model_id":"qwen3-vl-30b-a3b-thinking","model_name":"Qwen3 VL 30B A3B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.423,"normalized_score":0.423,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","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":31000000000,"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":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.411,"normalized_score":0.411,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"13","verification_date":null,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":2.4,"context_window":262144,"announcement_date":"2026-02-24","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":15,"model_id":"qwen3-vl-8b-thinking","model_name":"Qwen3 VL 8B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.398,"normalized_score":0.398,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.18,"output_cost_per_million":2.09,"context_window":262144,"announcement_date":"2025-09-22","param_count":9000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":16,"model_id":"qwen3-vl-4b-thinking","model_name":"Qwen3 VL 4B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.394,"normalized_score":0.394,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":"13","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":1.0,"context_window":262144,"announcement_date":"2025-09-22","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"}]}