AICA-Bench - Emotion Understanding (Basic): leaderboard
AICA-Bench emotion understanding with direct prompts: classify the emotion expressed in or evoked by an image from a fixed category list. Weighted F1 in percent, higher is better.
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 February 2027. 23 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 68.05 | #463 |
| 2 | Gemini 2.0 Flash | 67.16 | #723 |
| 3 | Gemini 2.5 Pro | 66.97 | #276 |
| 4 | GPT-4o | 64.44 | #751 |
| 5 | Qwen-VL-Max (AICA-Bench checkpoint unspecified) | 64.07 | |
| 6 | GPT-4o Mini | 60.15 | #1667 |
| 7 | Qwen-VL-Plus (AICA-Bench checkpoint unspecified) | 60.04 | |
| 8 | Qwen 2.5 VL 7B Instruct | 56.43 | #1902 |
| 9 | Qwen 2.5 VL 3B Instruct | 54.58 | #2713 |
| 10 | Ovis2-16B | 54.38 | #1594 |
| 11 | LLaVA-OneVision | 54.02 | #2028 |
| 12 | Ovis2-8B | 53.63 | #2047 |
| 13 | Qwen 2 VL 7B Instruct | 53.52 | #2573 |
| 14 | InternVL3-14B-Instruct | 52.91 | #1801 |
| 15 | MiniCPM-o-2.6 | 52.73 | #2423 |
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-understanding-basic · How It Works · Data refreshed daily, snapshot 2026-11-21.