Emotional intelligence in large language model: leaderboard
As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical frontier for safety and alignment. Current benchmarks often conflate superficial politeness with deep affective reasoning, failing to distinguish between perceptual accuracy and interactive efficacy. Here, we introduce FACE
Metric: Total Kappa (self-reported). Source: benchmarklist.com. Saturation forecast: Around December 2026. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 66.5 | #98 |
| 2 | Gemini 2.5 Pro | 64.1 | #152 |
| 3 | Seed-1.6 | 61.2 | #265 |
| 4 | O3 | 61.1 | #124 |
| 5 | Kimi K2 | 60.6 | #243 |
| 6 | DeepSeek R1 | 58.5 | #251 |
| 7 | Qwen 3 235B A22B | 56.5 | #313 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=emotional-intelligence-in-large-language-model · How It Works · Data refreshed daily, snapshot 2026-10-20.