MultiEmo-Bench: leaderboard
This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language models (MLLMs) to predict the emotions evoked by images. Recent user studies report an unintuitive finding: humans may prefer the predictions of MLLMs over the labels in existing datasets. We argue that this phenomenon stems from the suboptimal annot
Metric: Cosine (self-reported). Source: benchmarklist.com. Saturation forecast: Around April 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 81.3 | #343 |
| 2 | GPT-5 | 81.1 | #98 |
| 3 | GPT-5.1 | 81.1 | #135 |
| 4 | Claude Sonnet 4 | 75.6 | #199 |
| 5 | Gemini 3 Flash (Preview) | 75.3 | #82 |
| 6 | Gemini 2.5 Flash | 72.7 | #245 |
| 7 | GPT-5 Nano | 72.5 | #425 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=multiemo-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.