MVBench
Progress Over Time
Interactive timeline showing model performance evolution on MVBench
MVBench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Alibaba Cloud / Qwen Team | 122B | — | — | ||
| 2 | Alibaba Cloud / Qwen Team | 28B | 262K | $0.60 / $3.60 | ||
| 3 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 4 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 4 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 6 | Alibaba Cloud / Qwen Team | 73B | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 8 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 10 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 11 | Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 12 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 13 | Alibaba Cloud / Qwen Team | 8B | — | — | ||
| 14 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $1.00 | ||
| 15 | Alibaba Cloud / Qwen Team | 9B | — | — | ||
| 16 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $0.60 | ||
| 17 | Alibaba Cloud / Qwen Team | 9B | — | — |
What is MVBench?
A comprehensive multi-modal video understanding benchmark covering 20 challenging video tasks that require temporal understanding beyond single-frame analysis. Tasks span from perception to cognition, including action recognition, temporal reasoning, spatial reasoning, object interaction, scene transition, and counterfactual inference. Uses a novel static-to-dynamic method to systematically generate video tasks from existing annotations.
MVBench is a multimodal benchmark evaluating models on multimodal, reasoning, spatial reasoning, video, and vision tasks. LLM Stats tracks 17 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.8.
Compare leaders on the best AI for multimodal, best AI for reasoning, best AI for spatial reasoning, best AI for video and best AI for vision leaderboards.
Current leaders
Qwen3.5-122B-A10B from Alibaba Cloud / Qwen Team currently leads the MVBench leaderboard with a score of 0.766 across 17 evaluated AI models.
Source paper
- Title
- MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
- Authors
- Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, and 8 others
- Published
- arXiv
- 2311.17005
Abstract
With the rapid development of Multi-modal Large Language Models (MLLMs), a number of diagnostic benchmarks have recently emerged to evaluate the comprehension capabilities of these models. However, most benchmarks predominantly assess spatial understanding in the static image tasks, while overlooking temporal understanding in the dynamic video tasks. To alleviate this issue, we introduce a comprehensive Multi-modal Video understanding Benchmark, namely MVBench, which covers 20 challenging video tasks that cannot be effectively solved with a single frame. Specifically, we first introduce a novel static-to-dynamic method to define these temporal-related tasks. By transforming various static tasks into dynamic ones, we enable the systematic generation of video tasks that require a broad spectrum of temporal skills, ranging from perception to cognition. Then, guided by the task definition, we automatically convert public video annotations into multiple-choice QA to evaluate each task. On one hand, such a distinct paradigm allows us to build MVBench efficiently, without much manual intervention. On the other hand, it guarantees evaluation fairness with ground-truth video annotations, avoiding the biased scoring of LLMs. Moreover, we further develop a robust video MLLM baseline, i.e., VideoChat2, by progressive multi-modal training with diverse instruction-tuning data. The extensive results on our MVBench reveal that, the existing MLLMs are far from satisfactory in temporal understanding, while our VideoChat2 largely surpasses these leading models by over 15% on MVBench. All models and data are available at https://github.com/OpenGVLab/Ask-Anything.
FAQ
Common questions about the MVBench benchmark and leaderboard.