E3mo-Bench (Evoked) - Video-Pair Perception (Yes-or-No): leaderboard
E3mo-Bench (E³mo-Bench, 2026) evoked-emotion subset, about the emotion a video evokes in the viewer: yes-or-no questions comparing two videos on emotion, valence, arousal or dominance. Accuracy in percent; higher is better.
Metric: Accuracy (%; yes-or-no questions comparing the emotion, valence, arousal or dominance of two videos, among 2,375 video-pair questions; 16 MLLMs on videos from eight emotion datasets, each assigned one affective perspective; subset: the viewer's evoked emotion). Source: arxiv.org. Saturation forecast: Around 2030. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-8B | 61.2 | #1688 |
| 2 | GPT-5.4 | 57.74 | #123 |
| 3 | Claude Sonnet 4.6 | 52.95 | #161 |
| 4 | Qwen2.5-Omni-7B | 48.23 | #1789 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=e3mo-bench-evoked-video-pair-perception-yes-or-no · How It Works · Data refreshed daily, snapshot 2026-11-13.