AIM-Bench (Affective Image Manipulation) - Emotion Accuracy: leaderboard

AIM-Bench affective image editing scored by whether Gemini-2.5-Pro classifies the edited image as the target emotion among the eight Mikels categories. Accuracy in percent, higher is better.

Metric: Emotion accuracy (%): Gemini-2.5-Pro classifies each edited image into the 8 Mikels emotions, and an edit counts as correct when the predicted emotion is the target emotion, 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
1Step1X-Edit (AIM-Bench checkpoint unspecified)68.84
2Qwen-Image-Edit-250962.34
3Seedream 4.061.55
4UniWorld-V260.38
5Qwen-Image-Edit-Plus (AIM-Bench checkpoint unspecified)58.39
6FLUX-Kontext-Max57.01
7BAGEL-7B-MoT56#4619
8FLUX-Kontext-Pro54.77
9OmniGen254.37#4579
10SeedEdit 3.052.73
11FLUX.1-Kontext-dev50.88
12DreamOmni237.88
13InstructPix2Pix18.38

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