# MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark

arXiv: https://arxiv.org/abs/2601.02536 · HTML: https://mlsanity.com/paper/2601.02536/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos](https://mlsanity.com/paper/2501.13826/) (2025)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [Evaluating Factuality in Generation with Dependency-level Entailment](https://mlsanity.com/paper/2010.05478/) (2020)
- [VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation](https://mlsanity.com/paper/2406.19276/) (2024)
- [CinePile: A Long Video Question Answering Dataset and Benchmark](https://mlsanity.com/paper/2405.08813/) (2024)
- [Evaluating Open-Domain Question Answering in the Era of Large Language Models](https://mlsanity.com/paper/2305.06984/) (2023)
- [Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models](https://mlsanity.com/paper/2311.16103/) (2023)
- [Efficient Movie Scene Detection using State-Space Transformers](https://mlsanity.com/paper/2212.14427/) (2022)
- [DramaQA: Character-Centered Video Story Understanding with Hierarchical QA](https://mlsanity.com/paper/2005.03356/) (2020)
- [The Amazon Nova Family of Models: Technical Report and Model Card](https://mlsanity.com/paper/2506.12103/) (2025)
- [Learning to Answer Visual Questions from Web Videos](https://mlsanity.com/paper/2205.05019/) (2022)
- [InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows](https://mlsanity.com/paper/2406.19875/) (2024)
- [Shortcomings of Question Answering Based Factuality Frameworks for Error Localization](https://mlsanity.com/paper/2210.06748/) (2022)
- [Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models](https://mlsanity.com/paper/2503.18923/) (2025)

## Built on by (most cited first, 4 of 4)

- [TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos](https://mlsanity.com/paper/2605.07593/) (2026)
- [One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding](https://mlsanity.com/paper/2608.05707/) (2026)
- [Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision](https://mlsanity.com/paper/2609.04203/) (2026)
- [NEST: Narrative Event Structures in Time for Long Video Understanding](https://mlsanity.com/paper/2606.19706/) (2026)

## Abstract (arXiv)

Understanding real-world videos such as movies requires integrating visual and dialogue cues. Yet existing VideoQA benchmarks struggle to capture this multimodal reasoning and, given the difficulty of evaluating free-form answers, largely resort to simple multiple choice questions. We introduce a novel open-ended multimodal VideoQA benchmark, MovieRecapsQA, created using movie recap videos -- a distinctive type of YouTube content that summarizes a film via a voiceover description of key clips from the movie (recap video). From the transcribed voiceover (recap summary) of 60 recap videos, we generate ≈8.2K questions along with the necessary ``facts'' expected in each answer; the former facilitates the creation of questions that require mutimodal reasoning and the latter allow the construction of a reference-free evaluation metric that can be applied to open-ended responses. To our knowledge, this is the first reference-free open-ended VideoQA benchmark. The benchmark allows each question to be evaluated in different input video settings: given (a) the full-length movie, (b) the full (≈11 min) recap video (visual only), (c) ≈14 min of aligned movie scenes, i.e, movie scenes relevant to the question, and (d) ≈1.2 min of aligned recap video scenes. In all cases, the text of any associated movie dialogue is provided. Each question is categorized by the modality required to answer it -- visual, dialogue, or both -- enabling fine-grained evaluation of multimodal capabilities. We benchmark (setting (d)) seven state-of-the-art MLLMs and find that (i) only our reference-free metric produces meaningful human-aligned model separation; (ii) vision-centric questions yield the lowest scores across all models; (iii) removing visual input often textitimproves model factuality; and (iv) the primary bottleneck is visual perception, not visual reasoning.