DAR (Dynamic Affective Reasoning) - Affective Segmentation: leaderboard
DAR (Dynamic Affective Reasoning, 2026) affective segmentation: models split each of 1,441 test videos into segments where the viewer emotion changes. Mean temporal IoU with the ground-truth segments in percent, higher is better.
Metric: Mean temporal IoU (%; overlap between predicted and ground-truth affective segments; 1,441 test videos of the DAR viewer-centric emotion dataset (27 emotion categories, emotions changing across consecutive events); the model segments the video into affective segments, labels each segment's emotion and writes a causal rationale; off-the-shelf models without fine-tuning on DAR). Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 45.2 | #1833 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=dar-dynamic-affective-reasoning-affective-segmentation · How It Works · Data refreshed daily, snapshot 2026-11-13.