Benchmark

Social IQa

The first large-scale benchmark for commonsense reasoning about social situations. Contains 38,000 multiple choice questions probing emotional and social…

Modality
text
Categories
psychology, reasoning, creativity
Openness
unknown
Source
llm_stats
Reported scores
9

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemma 2 27BGoogle0.5372024-06-27evidence
Gemma 2 9BGoogle0.5342024-06-27evidence
Gemma 3n E2BGoogle0.4882025-06-26evidence
Gemma 3n E2B Instructed LiteRT (Preview)Google0.4882025-05-20evidence
Gemma 3n E4BGoogle0.52025-06-26evidence
Gemma 3n E4B Instructed LiteRT PreviewGoogle0.52025-05-20evidence
Phi 4 MiniMicrosoft0.7252025-02-01evidence
Phi-3.5-mini-instructMicrosoft0.7472024-08-23evidence
Phi-3.5-MoE-instructMicrosoft0.782024-08-23evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.