DAR (Dynamic Affective Reasoning) - Affective Segmentation: leaderboard
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 December 2026. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 45.2 |
| 2 | InternVL3.5-8B | 39.2 |
Interactive version: theaggregate.ai/benchmark?slug=dar-dynamic-affective-reasoning-affective-segmentation · How It Works · Data refreshed daily, snapshot 2026-09-29.