AttuneBench: leaderboard
Emotional intelligence (EI), the ability to perceive, understand, and respond appropriately to others' emotional states, is central to human communication, and increasingly important to assess as LLMs assume conversational roles in everyday life. Existing EI benchmarks rely on synthetic prompts, single-turn cases, or third-party annotation. These approaches do not directly measure how models infer
Metric: Composite (self-reported). Source: benchmarklist.com. Saturation forecast: Around September 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 54.3 | #63 |
| 2 | GPT-5.5 | 53.71 | #31 |
| 3 | Claude Opus 4.7 | 53.64 | #49 |
| 4 | MiMo-V2-Pro | 53.61 | #168 |
| 5 | Claude Haiku 4.5 | 52.83 | #280 |
| 6 | Qwen 2.5 72B | 52.23 | #499 |
| 7 | Claude Sonnet 4.6 | 50.29 | #90 |
| 8 | GPT-5.4 | 50.24 | #79 |
| 9 | Grok 4 | 50.14 | #181 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=attunebench · How It Works · Data refreshed daily, snapshot 2026-10-20.