OVIBench (Multiple Choice) - False Trigger: leaderboard
Answer-selection accuracy on false-trigger interruptions, where the model should ignore the interruption and continue in the OVIBench (2026) multiple-choice subset. Percent, higher is better.
Metric: Answer-selection accuracy (%; choosing, among four candidate continuations, the one that handles the interruption correctly; multiple-choice subset of 4,710 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); false-trigger interruptions, where the model should ignore the interruption and continue). Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 56.63 | #452 |
| 2 | Qwen 2.5 VL 7B | 43.46 | #1796 |
| 3 | Seed-1.6 | 30.28 | #447 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ovibench-multiple-choice-false-trigger · How It Works · Data refreshed daily, snapshot 2026-11-12.