OVIBench (Open-Ended) - Interruption Type Classification: leaderboard
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 |
|---|---|---|
| 1 | Seed-1.6 | 92.85 |
| 2 | Qwen 3 VL 8B | 88.61 |
| 3 | Qwen 2.5 VL 7B | 83.64 |
| 4 | Gemini 2.5 Flash | 73.39 |
Interactive version: theaggregate.ai/benchmark?slug=ovibench-open-ended-interruption-type-classification · How It Works · Data refreshed daily, snapshot 2026-09-26.