{"benchmark_id":"social-iqa","name":"Social IQa","parent_benchmark":null,"categories":["psychology","reasoning","creativity"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"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.","paper_link":"https://arxiv.org/abs/1904.09728","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.188136+00:00","updated_at":"2026-07-05T18:28:00.619753+00:00","statistics":{"total_models":9,"average_score":0.5887777777777777,"min_score":0.488,"max_score":0.78,"score_stddev":0.12344713218396144,"verified_count":0,"self_reported_count":9},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.78,"normalized_score":0.78,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct","analysis_method":"5-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":60000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.747,"normalized_score":0.747,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct","analysis_method":"5-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":3800000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"phi-4-mini","model_name":"Phi 4 Mini","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.725,"normalized_score":0.725,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-4-mini-instruct","analysis_method":"5-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-01","param_count":3840000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"gemma-2-27b-it","model_name":"Gemma 2 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.537,"normalized_score":0.537,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma2","analysis_method":"0-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-06-27","param_count":27200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"gemma-2-9b-it","model_name":"Gemma 2 9B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.534,"normalized_score":0.534,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma2","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-06-27","param_count":9240000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"gemma-3n-e4b","model_name":"Gemma 3n E4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.5,"normalized_score":0.5,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B","analysis_method":"0-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.5,"normalized_score":0.5,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.488,"normalized_score":0.488,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemma-3n-e2b","model_name":"Gemma 3n E2B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.488,"normalized_score":0.488,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B","analysis_method":"0-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}