{"benchmark_id":"longvideobench","name":"LongVideoBench","parent_benchmark":null,"categories":["multimodal","long_context","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"LongVideoBench is a question-answering benchmark featuring video-language interleaved inputs up to an hour long. It includes 3,763 varying-length web-collected videos with subtitles across diverse themes and 6,678 human-annotated multiple-choice questions in 17 fine-grained categories for comprehensive evaluation of long-term multimodal understanding.","paper_link":"https://arxiv.org/abs/2407.15754","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.211695+00:00","updated_at":"2026-07-05T18:27:51.766849+00:00","statistics":{"total_models":4,"average_score":0.7392500000000001,"min_score":0.547,"max_score":0.806,"score_stddev":0.12822213797416837,"verified_count":0,"self_reported_count":4},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"seed-2.1-pro","model_name":"Seed 2.1 Pro","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.806,"normalized_score":0.806,"verified":false,"self_reported":true,"self_reported_source":"https://seed.bytedance.com/en/seed2_1","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-24","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":1,"model_id":"seed-2.1-turbo","model_name":"Seed 2.1 Turbo","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.806,"normalized_score":0.806,"verified":false,"self_reported":true,"self_reported_source":"https://seed.bytedance.com/en/seed2_1","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-24","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":3,"model_id":"kimi-k2.5","model_name":"Kimi K2.5","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.798,"normalized_score":0.798,"verified":false,"self_reported":true,"self_reported_source":"https://fireworks.ai/models/fireworks/kimi-k2p5","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":4,"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":0.547,"normalized_score":0.547,"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}]}