NICE: leaderboard
As large language models (LLMs) are increasingly applied in social contexts such as emotional companionship and customer service, measuring their social intelligence has become critical to the quality and safety of human-AI interaction. However, existing social intelligence benchmarks lack a unified framework that organizes social abilities into a unified structure, and therefore cannot enable fin
Metric: Weighted All (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78.1 | #58 |
| 2 | GPT-5.5 | 76 | #31 |
| 3 | DeepSeek V4 Pro | 73.4 | #102 |
| 4 | Qwen 3.6 Plus | 71.4 | #120 |
| 5 | Claude Opus 4.7 | 70.5 | #49 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=nice · How It Works · Data refreshed daily, snapshot 2026-10-20.