EIBench (complex): leaderboard
Harder split of the Emotional Intelligence Benchmark with multi-emotion and ambiguous scenarios requiring nuanced affective reasoning.
Metric: Recall. Source: huggingface.co. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | ChatGPT 4o | 39.27 | #282 |
| 2 | Claude 3 Haiku | 24 | #803 |
| 3 | Claude 3 Sonnet | 21.37 | #775 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=eibench-complex · How It Works · Data refreshed daily, snapshot 2026-10-20.