{"benchmark_id":"humaneval-mul","name":"HumanEval-Mul","parent_benchmark":null,"categories":["reasoning"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","description":"A multilingual variant of the HumanEval benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics","paper_link":"https://arxiv.org/abs/2107.03374","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.888066+00:00","updated_at":"2026-07-05T18:27:50.090801+00:00","statistics":{"total_models":2,"average_score":0.782,"min_score":0.738,"max_score":0.826,"score_stddev":0.06222539674441608,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"deepseek-v3","model_name":"DeepSeek-V3","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.826,"normalized_score":0.826,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/deepseek-ai/DeepSeek-V3","analysis_method":"Pass@1","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":2,"model_id":"deepseek-v2.5","model_name":"DeepSeek-V2.5","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.738,"normalized_score":0.738,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V2.5","analysis_method":"Pass@1","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-08","param_count":236000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}