OVIBench (Open-Ended) - Interruption Type Classification: leaderboard
OVIBench (2026) evaluates how vision-language models handle user interruptions while answering questions about streaming video, using an offline simulation of interruptions during answer generation. Accuracy of classifying the interruption as false trigger, correction or cancellation on the open-ended subset, in percent; higher is better.
Metric: Classification accuracy (%; interruption identified as false trigger, correction or cancellation; open-ended subset of 13,145 samples; offline simulation of an interruption arriving while the model is generating its answer about a streaming video (3,200 videos from ActivityNet, MovieChat, QVHighlights, UCF-Crime and YouCook2)). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed-1.6 | 92.85 | #447 |
| 2 | Qwen 2.5 VL 7B | 83.64 | #1796 |
| 3 | Gemini 2.5 Flash | 73.39 | #452 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ovibench-open-ended-interruption-type-classification · How It Works · Data refreshed daily, snapshot 2026-11-12.