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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Step1X-Edit (AIM-Bench checkpoint unspecified) | 68.84 | |
| 2 | Qwen-Image-Edit-2509 | 62.34 | |
| 3 | Seedream 4.0 | 61.55 | |
| 4 | UniWorld-V2 | 60.38 | |
| 5 | Qwen-Image-Edit-Plus (AIM-Bench checkpoint unspecified) | 58.39 | |
| 6 | FLUX-Kontext-Max | 57.01 | |
| 7 | BAGEL-7B-MoT | 56 | #4619 |
| 8 | FLUX-Kontext-Pro | 54.77 | |
| 9 | OmniGen2 | 54.37 | #4579 |
| 10 | SeedEdit 3.0 | 52.73 | |
| 11 | FLUX.1-Kontext-dev | 50.88 | |
| 12 | DreamOmni2 | 37.88 | |
| 13 | InstructPix2Pix | 18.38 |
Interactive version: theaggregate.ai/benchmark?slug=aim-bench-affective-image-manipulation-emotion-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-21.