{"benchmark_id":"mmvu","name":"MMVU","parent_benchmark":null,"categories":["multimodal","reasoning","video","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"MMVU (Multimodal Multi-disciplinary Video Understanding) is a benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, testing comprehension and reasoning capabilities on video content.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.054570+00:00","updated_at":"2026-10-31T18:28:31.495484+00:00","statistics":{"total_models":7,"average_score":0.7475714285714287,"min_score":0.69,"max_score":0.805,"score_stddev":0.04259834559720659,"verified_count":0,"self_reported_count":7},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"glm-5.3-flash","model_name":"GLM-5.3-Flash","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.805,"normalized_score":0.805,"verified":false,"self_reported":true,"self_reported_source":"https://z.ai/blog/glm-5.3-flash","analysis_method":"Native video input; temp=1.0 top_p=0.95; 256K context","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.15,"output_cost_per_million":0.5,"context_window":1048576,"announcement_date":"2026-08-26","param_count":320000000000,"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":"kimi-k2.5","model_name":"Kimi K2.5","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.804,"normalized_score":0.804,"verified":false,"self_reported":true,"self_reported_source":"https://www.kimi.com/blog/kimi-k2-5.html","analysis_method":"Video","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-01-27","param_count":1000000000000,"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":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.747,"normalized_score":0.747,"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":4,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.733,"normalized_score":0.733,"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":5,"model_id":"seed-1.8","model_name":"Seed 1.8","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.731,"normalized_score":0.731,"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 3; think-high; public video evaluation","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":6,"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":0.723,"normalized_score":0.723,"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":7,"model_id":"seed-2.0-mini","model_name":"Seed 2.0 Mini","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.69,"normalized_score":0.69,"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 9 public video benchmarks; reported 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"}]}