{"benchmark_id":"videomme-w-sub.","name":"VideoMME w sub.","parent_benchmark":null,"categories":["multimodal","video","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"The first-ever comprehensive evaluation benchmark of Multi-modal LLMs in Video analysis. Features 900 videos (254 hours) with 2,700 question-answer pairs covering 6 primary visual domains and 30 subfields. Evaluates temporal understanding across short (11 seconds) to long (1 hour) videos with multi-modal inputs including video frames, subtitles, and audio.","paper_link":"https://arxiv.org/abs/2405.21075","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.782327+00:00","updated_at":"2026-07-05T18:28:04.840877+00:00","statistics":{"total_models":9,"average_score":0.8264444444444444,"min_score":0.716,"max_score":0.877,"score_stddev":0.0673964225888717,"verified_count":0,"self_reported_count":9},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.877,"normalized_score":0.877,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-27b","analysis_method":"With subtitles","verification_date":null,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"context_window":262144,"announcement_date":"2026-04-21","param_count":27781427952,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":2,"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":0.873,"normalized_score":0.873,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"With subtitles","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":3,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.87,"normalized_score":0.87,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"With subtitles","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":4,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.867,"normalized_score":0.867,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"VideoMME (long) with subtitles category.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-08-07","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":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.866,"normalized_score":0.866,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"With subtitles","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":5,"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":0.866,"normalized_score":0.866,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":"With subtitles","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":7,"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":0.779,"normalized_score":0.779,"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":8,"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":0.724,"normalized_score":0.724,"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":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":0.716,"normalized_score":0.716,"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}]}