{"benchmark_id":"cluewsc","name":"CLUEWSC","parent_benchmark":null,"categories":["reasoning","language"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","description":"CLUEWSC2020 is the Chinese version of the Winograd Schema Challenge, part of the CLUE benchmark. It focuses on pronoun disambiguation and coreference resolution, requiring models to determine which noun a pronoun refers to in a sentence. The dataset contains 1,244 training samples and 304 development samples extracted from contemporary Chinese literature.","paper_link":"https://arxiv.org/abs/2004.05986","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.397162+00:00","updated_at":"2026-07-05T18:27:45.398165+00:00","statistics":{"total_models":3,"average_score":0.7696666666666667,"min_score":0.486,"max_score":0.914,"score_stddev":0.24567525991302694,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"kimi-k1.5","model_name":"Kimi-k1.5","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.914,"normalized_score":0.914,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/MoonshotAI/Kimi-k1.5","analysis_method":"Exact Match","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"deepseek-v3","model_name":"DeepSeek-V3","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.909,"normalized_score":0.909,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/deepseek-ai/DeepSeek-V3","analysis_method":"Exact Match","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-25","param_count":671000000000,"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":"ernie-4.5","model_name":"ERNIE 4.5","organization_id":"baidu","organization_name":"Baidu","organization_country":"CN","score":0.486,"normalized_score":0.486,"verified":false,"self_reported":true,"self_reported_source":"https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-25","param_count":21000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}