AICA-Bench - Emotion Understanding (CoT): leaderboard
AICA-Bench emotion understanding with chain-of-thought prompts that reason over color, scene and facial cues before classifying the emotion of an image. Weighted F1 in percent, higher is better.
Metric: Weighted F1 (%) of emotion classification (expressed emotion recognition and evoked emotion prediction) with chain-of-thought prompts that reason over color, scene and facial cues first, 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 | 69.32 | #463 |
| 2 | Gemini 2.0 Flash | 68.98 | #723 |
| 3 | Qwen-VL-Plus (AICA-Bench checkpoint unspecified) | 67.81 | |
| 4 | Gemini 2.5 Pro | 67.57 | #276 |
| 5 | Qwen-VL-Max (AICA-Bench checkpoint unspecified) | 65.98 | |
| 6 | GPT-4o | 65.42 | #751 |
| 7 | GPT-4o Mini | 63.68 | #1667 |
| 8 | Qwen 2.5 VL 7B Instruct | 57.25 | #1902 |
| 9 | Qwen 2 VL 7B Instruct | 55.19 | #2573 |
| 10 | Ovis2-16B | 54.7 | #1594 |
| 11 | Qwen 2.5 VL 3B Instruct | 53.67 | #2713 |
| 12 | LLaVA-OneVision | 53.25 | #2028 |
| 13 | InternVL3-8B-Instruct | 52.98 | #2872 |
| 14 | Ovis2-8B | 52.73 | #2047 |
| 15 | InternVL3-14B-Instruct | 52.04 | #1801 |
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-cot · How It Works · Data refreshed daily, snapshot 2026-11-21.