Social IQa: leaderboard
38,000 three-option multiple-choice questions about everyday social situations, asking about people's motivations, emotional reactions and likely next actions; Allen Institute for AI (EMNLP 2019).
Metric: Score (%). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o Mini (2024-07-18) | 82.9 | #558 |
| 2 | Phi-3.5-MoE-instruct | 78 | #700 |
| 3 | Gemini 1.5 Flash | 77.8 | #618 |
| 4 | Gemma 2 9B (IT) | 74.7 | #788 |
| 5 | Llama 3.1 8B Instruct | 71.8 | #1035 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=social-iqa · How It Works · Data refreshed daily, snapshot 2026-10-20.