VidMsg QA (YouTube Input): leaderboard
The VidMsg (2026) implicit-message multiple-choice probe run with native YouTube access, so the model receives each clip as video with audio rather than sampled frames: pick the intended message of a short clip from five same-topic options. Accuracy in percent (chance 20); higher is better.
Metric: Overall accuracy (%), five-option multiple choice: pick the intended implicit message of a short YouTube clip from distractors sampled within the same topic (one question per clip over 9 topics and 52 target messages; the per-topic cells imply 395 scored clips); chance 20; the model receives the clip through native YouTube URL access (video with audio) instead of sampled frames; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.5 | #94 |
| 2 | Gemini 3 Flash | 76.5 | #164 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=vidmsg-qa-youtube-input · How It Works · Data refreshed daily, snapshot 2026-11-13.