AICA-Bench - Emotion Understanding (Basic): leaderboard
Metric: Weighted F1 (%) of emotion classification (expressed emotion recognition and evoked emotion prediction from a predefined category list) with basic direct prompts 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 January 2027. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 68.05 |
| 2 | Gemini 2.0 Flash | 67.16 |
| 3 | Gemini 2.5 Pro | 66.97 |
| 4 | GPT-4o | 64.44 |
| 5 | GPT-4o Mini | 60.15 |
| 6 | Qwen 2.5 VL 7B Instruct | 56.43 |
| 7 | Qwen 2 VL 7B Instruct | 53.52 |
| 8 | MiniCPM-V-2.6 | 43.7 |
Interactive version: theaggregate.ai/benchmark?slug=aica-bench-emotion-understanding-basic · How It Works · Data refreshed daily, snapshot 2026-10-07.