MOV-Bench: leaderboard
MOV-Bench (Xu et al., 2026) has 519 multiple-choice questions on FineVideo clips that need two to four hops of reasoning over evidence spread across several segments and across both the audio and the visual stream; questions answerable from language alone were filtered out and the rest human-verified. Accuracy in percent when the omni-modal model answers directly from the whole video; higher is better.
Metric: Accuracy (%; 519 audio-visual multi-hop multiple-choice questions; direct inference on the whole video). Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen3 Omni 30B A3B Instruct | 52.79 | #902 |
| 2 | Qwen2.5-Omni-7B | 46.63 | #1797 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mov-bench · How It Works · Data refreshed daily, snapshot 2026-11-12.