{"benchmark_id":"repobench","name":"RepoBench","parent_benchmark":null,"categories":["reasoning","code"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"RepoBench is a benchmark for evaluating repository-level code auto-completion systems through three interconnected tasks: RepoBench-R (retrieval of relevant code snippets across files), RepoBench-C (code completion with cross-file and in-file context), and RepoBench-P (pipeline combining retrieval and prediction). Supports Python and Java programming languages and addresses the gap in evaluating real-world, multi-file programming scenarios by providing a more complete comparison of performance in auto-completion systems.","paper_link":"https://arxiv.org/abs/2306.03091","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.924369+00:00","updated_at":"2026-07-05T18:27:59.710854+00:00","statistics":{"total_models":1,"average_score":0.34,"min_score":0.34,"max_score":0.34,"score_stddev":null,"verified_count":0,"self_reported_count":1},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"codestral-22b","model_name":"Codestral-22B","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.34,"normalized_score":0.34,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/codestral/","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":"2024-05-29","param_count":22200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}