What is the Social IQa leaderboard?

The Social IQa leaderboard ranks 9 AI models based on their performance on this benchmark. Currently, Phi-3.5-MoE-instruct by Microsoft leads with a score of 0.780. The average score across all models is 0.589.

What is the highest Social IQa score?

The highest Social IQa score is 0.780, achieved by Phi-3.5-MoE-instruct from Microsoft.

How many models are evaluated on Social IQa?

9 models have been evaluated on the Social IQa benchmark, with 0 verified results and 9 self-reported results.

Where can I find the Social IQa paper?

The Social IQa paper is available at https://arxiv.org/abs/1904.09728. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does Social IQa cover?

Social IQa is categorized under creativity, psychology, and reasoning. The benchmark evaluates text models.

What is the best open-source model on Social IQa?

Phi-3.5-MoE-instruct by Microsoft is the top-ranked open-source model on Social IQa, with a score of 0.780 (rank #1).

How recent are the Social IQa leaderboard results?

The Social IQa leaderboard was last updated in May 2026 and currently includes 9 evaluated models.

All benchmarks

Social IQa

The first large-scale benchmark for commonsense reasoning about social situations. Contains 38,000 multiple choice questions probing emotional and social intelligence in everyday situations, testing commonsense understanding of social interactions and theory of mind reasoning about the implied emotions and behavior of others.

Phi-3.5-MoE-instruct from Microsoft currently leads the Social IQa leaderboard with a score of 0.780 across 9 evaluated AI models.

Paper