AICA-Bench - Emotion-Guided Generation: leaderboard
AICA-Bench emotion-guided content generation: describe an image so that the text conveys a target emotion, rated 1 to 5 by a scoring model trained on human ratings, rescaled to 20-100. Higher is better.
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 February 2027. 23 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen-VL-Max (AICA-Bench checkpoint unspecified) | 75.93 | |
| 2 | GPT-4o | 75.73 | #751 |
| 3 | Gemini 2.5 Pro | 74.13 | #276 |
| 4 | GPT-4o Mini | 74.09 | #1667 |
| 5 | Ovis2-16B | 71.56 | #1594 |
| 6 | Ovis2-8B | 70.81 | #2047 |
| 7 | InternVL2.5-8B | 68.86 | #2370 |
| 8 | Gemini 2.5 Flash | 68.19 | #463 |
| 9 | InternVL3-8B-Instruct | 67.27 | #2872 |
| 10 | Qwen-VL-Plus (AICA-Bench checkpoint unspecified) | 66.86 | |
| 11 | InternVL3-14B-Instruct | 66.5 | #1801 |
| 12 | Ovis2-2B | 66.04 | #3863 |
| 13 | Qwen 2.5 VL 7B Instruct | 66 | #1902 |
| 14 | MiniCPM-o-2.6 | 64.98 | #2423 |
| 15 | Qwen 2 VL 7B Instruct | 64.76 | #2573 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=aica-bench-emotion-guided-generation · How It Works · Data refreshed daily, snapshot 2026-11-21.