{"benchmark_id":"multi-swe-bench","name":"Multi-SWE-Bench","parent_benchmark":null,"categories":["reasoning","code"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","description":"A multilingual benchmark for issue resolving that evaluates Large Language Models' ability to resolve software issues across diverse programming ecosystems. Covers 7 programming languages (Java, TypeScript, JavaScript, Go, Rust, C, and C++) with 1,632 high-quality instances carefully annotated by 68 expert annotators. Addresses limitations of existing benchmarks that focus almost exclusively on Python.","paper_link":"https://arxiv.org/abs/2504.02605","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.249747+00:00","updated_at":"2026-07-05T18:27:56.377139+00:00","statistics":{"total_models":6,"average_score":0.42883333333333334,"min_score":0.258,"max_score":0.527,"score_stddev":0.10460863571745246,"verified_count":0,"self_reported_count":6},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.527,"normalized_score":0.527,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/models/text/m27","analysis_method":null,"verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":204800,"announcement_date":"2026-03-18","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"MiniMax","best_throughput":null,"throughput_provider":"MiniMax","context_provider":"Novita"},{"rank":2,"model_id":"minimax-m2.5","model_name":"MiniMax M2.5","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.513,"normalized_score":0.513,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/news/minimax-m25","analysis_method":null,"verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2026-02-12","param_count":230000000000,"is_open_source":true,"is_new":false,"best_latency":3.0,"latency_provider":"MiniMax","best_throughput":100.0,"throughput_provider":"MiniMax","context_provider":"MiniMax"},{"rank":3,"model_id":"minimax-m2.1","model_name":"MiniMax M2.1","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.494,"normalized_score":0.494,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/news/minimax-m2-1","analysis_method":null,"verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2025-12-23","param_count":230000000000,"is_open_source":true,"is_new":false,"best_latency":3.0,"latency_provider":"MiniMax","best_throughput":100.0,"throughput_provider":"MiniMax","context_provider":"MiniMax"},{"rank":4,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.419,"normalized_score":0.419,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/thinking.html","analysis_method":"w/ tools","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-05","param_count":1000000000000,"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":"minimax-m2","model_name":"MiniMax M2","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.362,"normalized_score":0.362,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2025-10-27","param_count":230000000000,"is_open_source":true,"is_new":false,"best_latency":4.0,"latency_provider":"MiniMax","best_throughput":70.0,"throughput_provider":"MiniMax","context_provider":"MiniMax"},{"rank":6,"model_id":"qwen3-coder-480b-a35b-instruct","model_name":"Qwen3-Coder 480B A35B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.258,"normalized_score":0.258,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-coder/","analysis_method":"mini variant","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-31","param_count":480000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}