AICA-Bench - Emotion Reasoning: leaderboard
AICA-Bench emotion reasoning: explain why an image evokes its labeled emotion, rated 1 to 5 by a scoring model trained on human ratings for alignment, descriptiveness and causal soundness, rescaled to 20-100. Higher is better.
Metric: Emotion reasoning score on a percent scale: the model explains why an image evokes its labeled emotion, scored by the AICA-Bench scoring model (Qwen2.5-VL-7B fine-tuned on human 1-5 ratings) on emotion alignment and descriptiveness and causal soundness, 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 | Gemini 2.5 Pro | 79.08 | #280 |
| 2 | GPT-4o | 77.81 | #754 |
| 3 | Qwen-VL-Max (AICA-Bench checkpoint unspecified) | 77.75 | |
| 4 | Gemini 2.5 Flash | 76.55 | #466 |
| 5 | GPT-4o Mini | 76.45 | #1680 |
| 6 | Qwen 2.5 VL 7B Instruct | 74.5 | #1919 |
| 7 | LLaVA-1.6-7B | 73.81 | #4990 |
| 8 | LLaVA-1.6-13B | 73.57 | #6010 |
| 9 | Qwen-VL-Plus (AICA-Bench checkpoint unspecified) | 72.39 | |
| 10 | Gemini 2.0 Flash | 71.05 | #731 |
| 11 | MiniCPM-o-2.6 | 70.16 | #2442 |
| 12 | Qwen 2.5 VL 3B Instruct | 69.68 | #2720 |
| 13 | Ovis2-8B | 68.89 | #2059 |
| 14 | InternVL3-14B-Instruct | 68.27 | #1810 |
| 15 | Ovis2-16B | 68.24 | #1608 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=aica-bench-emotion-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-22.