AIM-Bench (Affective Image Manipulation) - Perceptual Quality: leaderboard

AIM-Bench affective image editing scored by the VIEScore perceptual quality rating of naturalness and freedom from artifacts, on a 0 to 10 scale, higher is better.

Metric: VIEScore PQ (0-10): naturalness of the edited image, structural fidelity and absence of distortions, over the 800 AIM-Bench affective image editing items (EmoSet source images, a target Mikels emotion with target valence-arousal-dominance coordinates and an editing instruction; 8 emotion categories, 5 editing types), each model run once with its official default settings; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Seedream 4.06.97
2FLUX-Kontext-Pro6.77
3FLUX-Kontext-Max6.77
4Qwen-Image-Edit-25096.4
5UniWorld-V26.22
6DreamOmni26.11
7Qwen-Image-Edit-Plus (AIM-Bench checkpoint unspecified)6.11
8SeedEdit 3.06.02
9OmniGen25.97#4579
10Step1X-Edit (AIM-Bench checkpoint unspecified)5.89
11FLUX.1-Kontext-dev5.66
12InstructPix2Pix4.62
13BAGEL-7B-MoT3.66#4619

Interactive version: theaggregate.ai/benchmark?slug=aim-bench-affective-image-manipulation-perceptual-quality · How It Works · Data refreshed daily, snapshot 2026-11-21.