AICA-Bench - Emotion-Guided Generation: leaderboard
Metric: Emotion-guided content generation score on a percent scale: the model writes a scene description congruent with a target emotion, scored by the AICA-Bench scoring model (Qwen2.5-VL-7B fine-tuned on human 1-5 ratings) on emotion alignment and descriptiveness, ratings rescaled as s/5 x 100 (20-100), over AICA-Bench (8,086 affective images from nine public emotion datasets with GPT-4o-generated instructions; closed-source models through their APIs at standard settings, open models on A100 GPUs); higher is better. Source: arxiv.org. Saturation forecast: Around December 2027. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 75.73 |
| 2 | Gemini 2.5 Pro | 74.13 |
| 3 | GPT-4o Mini | 74.09 |
| 4 | Gemini 2.5 Flash | 68.19 |
| 5 | Qwen 2.5 VL 7B Instruct | 66 |
| 6 | Qwen 2 VL 7B Instruct | 64.76 |
| 7 | Gemini 2.0 Flash | 63.93 |
| 8 | MiniCPM-V-2.6 | 63 |
Interactive version: theaggregate.ai/benchmark?slug=aica-bench-emotion-guided-generation · How It Works · Data refreshed daily, snapshot 2026-10-07.