TwinPast 基准：流式视频模型真的会用历史画面吗
TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs
做视频理解或评测的值得看这个新基准：现有榜单上高分模型换个测法就露馅，历史证据基本没用上。
TwinPast 基准用 350 组人工审核的视频对测试流式视频模型是否真正利用历史证据，每组视频对保持近期画面、问题和选项不变，仅改变关键历史证据。研究团队发现 OVO-Bench 和 StreamingBench 中 32% 的历史问题仅靠近期帧就能答对。评测覆盖 34 个模型配置，最强流式系统 PairAcc 只有 49.14%，通用模型则达到 66.57%-91.43%。Qwen3-VL-8B 和 DeepSeek-Flash 在加入历史输入后成绩反而超过仅用近期帧的表现。
TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs
High accuracy on streaming video benchmarks does not establish whether a model uses visual history. Our review of OVO-Bench and StreamingBench finds that recent frames suffice for 32% of sampled historical questions, while models also answer many questions correctly from the question and options alone. We introduce TwinPast to test whether answers correctly follow changes in history, using 350 human-reviewed video pairs spanning five historical tasks. Each pair holds the recent video context, question, and ordered options fixed while changing critical historical evidence and the correct answer. Each video is evaluated independently, and PairAcc requires correct answers for both histories. We evaluate 34 model and input configurations. For Qwen3-VL-8B and DeepSeek-Flash, historical inputs improve performance on TwinPast, reversing the recent-frame advantage on existing benchmarks. The strongest evaluated streaming system reaches 49.14% PairAcc, compared with 66.57-91.43% for the evaluated general-purpose models. This gap persists across all five tasks. Case studies further show that models select states from the wrong time or contradict recorded event order despite retaining the relevant evidence. These findings highlight the need to connect historical memory and retrieval with reasoning that uses evidence according to the question's temporal references and event relations.