VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
This work addresses a critical evaluation gap for researchers and developers in video AI, exposing deficiencies in grounded reasoning, though it is incremental as it builds on existing benchmarking efforts.
The paper tackles the problem of inflated performance in video multimodal large language models by introducing VideoZeroBench, a hierarchical benchmark for long-video question answering that verifies spatio-temporal evidence, and finds that even top models like Gemini-3-Pro achieve less than 17% accuracy in standard QA and drop below 1% when strict grounding is required.
Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual understanding and reasoning, and (2) answer correctness is often measured without verifying whether models identify the precise spatio-temporal evidence supporting their predictions. To address this, we present VideoZeroBench, a hierarchical benchmark designed for challenging long-video question answering that rigorously verifies spatio-temporal evidence. It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence. To disentangle answering generation, temporal grounding, and spatial grounding, we introduce a five-level evaluation protocol that progressively tightens evidence requirements. Experiments show that even Gemini-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting (Level-3). When grounding constraints are imposed, performance drops sharply: No model exceeds 1% accuracy when both correct answering and accurate spatio-temporal localization are required (Level-5), with most failing to achieve any correct grounded predictions. These results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning, revealing that grounded video understanding remains a bottleneck for long-video QA. We further analyze performance across minimal evidence spans, atomic abilities, and inference paradigms, providing insights for future research in grounded video reasoning. The benchmark and code will be made publicly available.