{"benchmark_id":"swe-bench-multilingual","benchmark_name":"SWE-bench Multilingual","benchmark_description":"A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++. Contains 1,632 high-quality instances carefully annotated from 2,456 candidates by 68 expert annotators, designed to evaluate Large Language Models across diverse software ecosystems beyond Python.","max_score":1.0,"categories":["reasoning","code"],"modality":"text","total_models":39,"entries":[{"rank":1,"model_id":"claude-mythos-preview","model_name":"Claude Mythos Preview","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.873,"normalized_score":0.873,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":null,"announcement_date":"2026-04-07","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"claude-opus-4-8","model_name":"Claude Opus 4.8","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.844,"normalized_score":0.844,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-05-28","announcement_date":"2026-05-28","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"qwen3.8-flash-next","model_name":"Qwen3.8-Flash-Next","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.81,"normalized_score":0.81,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-08-26","announcement_date":"2026-08-26","multimodal":true,"param_count":125000000000,"is_new":true},{"rank":4,"model_id":"laguna-s-2.1","model_name":"Laguna S 2.1","organization_name":"Poolside","organization_id":"poolside","benchmark_score":0.785,"normalized_score":0.785,"verified":false,"self_reported":true,"provider_id":"poolside","input_cost_per_million":0.1,"output_cost_per_million":0.2,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-21","announcement_date":"2026-07-21","multimodal":false,"param_count":118000000000,"is_new":false},{"rank":5,"model_id":"claude-sonnet-5","model_name":"Claude Sonnet 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.783,"normalized_score":0.783,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":2.0,"output_cost_per_million":10.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-06-30","announcement_date":"2026-06-30","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.783,"normalized_score":0.783,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"speed_rps":null,"context_window":1000000,"release_date":"2026-05-19","announcement_date":"2026-05-19","multimodal":false,"param_count":null,"is_new":false},{"rank":7,"model_id":"claude-opus-4-6","model_name":"Claude Opus 4.6","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.7783,"normalized_score":0.7783,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-02-05","announcement_date":"2026-02-05","multimodal":true,"param_count":null,"is_new":false},{"rank":8,"model_id":"kimi-k2.6","model_name":"Kimi K2.6","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.767,"normalized_score":0.767,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.75,"output_cost_per_million":3.5,"speed_rps":null,"context_window":262144,"release_date":"2026-04-20","announcement_date":"2026-04-20","multimodal":true,"param_count":1000000000000,"is_new":false},{"rank":9,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.765,"normalized_score":0.765,"verified":false,"self_reported":true,"provider_id":"fireworks","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":196608,"release_date":"2026-03-18","announcement_date":"2026-03-18","multimodal":false,"param_count":null,"is_new":false},{"rank":10,"model_id":"deepseek-v4-pro-max","model_name":"DeepSeek-V4-Pro-Max","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.762,"normalized_score":0.762,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-04-23","announcement_date":"2026-04-23","multimodal":false,"param_count":1600000000000,"is_new":false},{"rank":11,"model_id":"hy3","model_name":"Hy3","organization_name":"Tencent","organization_id":"tencent","benchmark_score":0.758,"normalized_score":0.758,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-07-06","announcement_date":"2026-07-06","multimodal":false,"param_count":295000000000,"is_new":false},{"rank":12,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.758,"normalized_score":0.758,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-05-31","announcement_date":"2026-05-31","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.738,"normalized_score":0.738,"verified":false,"self_reported":true,"provider_id":"together","input_cost_per_million":0.5,"output_cost_per_million":3.0,"speed_rps":null,"context_window":1000000,"release_date":"2026-03-31","announcement_date":"2026-04-02","multimodal":true,"param_count":null,"is_new":false},{"rank":14,"model_id":"deepseek-v4-flash-max","model_name":"DeepSeek-V4-Flash-Max","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.733,"normalized_score":0.733,"verified":false,"self_reported":true,"provider_id":"deepseek","input_cost_per_million":0.14,"output_cost_per_million":0.28,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-23","announcement_date":"2026-04-23","multimodal":false,"param_count":284000000000,"is_new":false},{"rank":15,"model_id":"kimi-k2.5","model_name":"Kimi K2.5","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.73,"normalized_score":0.73,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-01-27","announcement_date":"2026-01-27","multimodal":true,"param_count":1000000000000,"is_new":false},{"rank":16,"model_id":"minimax-m2.1","model_name":"MiniMax M2.1","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.725,"normalized_score":0.725,"verified":false,"self_reported":true,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":100.0,"context_window":1000000,"release_date":"2025-12-23","announcement_date":"2025-12-23","multimodal":false,"param_count":230000000000,"is_new":false},{"rank":17,"model_id":"mimo-v2-pro","model_name":"MiMo-V2-Pro","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.717,"normalized_score":0.717,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-03-18","announcement_date":"2026-03-18","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":18,"model_id":"mimo-v2-flash","model_name":"MiMo-V2-Flash","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.717,"normalized_score":0.717,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-12-16","announcement_date":"2025-12-16","multimodal":false,"param_count":309000000000,"is_new":false},{"rank":19,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.713,"normalized_score":0.713,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"speed_rps":null,"context_window":262144,"release_date":"2026-04-21","announcement_date":"2026-04-21","multimodal":true,"param_count":27781427952,"is_new":false},{"rank":20,"model_id":"deepseek-v4-flash-0423","model_name":"DeepSeek-V4-Flash-0423","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.702,"normalized_score":0.702,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.2,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-23","announcement_date":"2026-04-23","multimodal":false,"param_count":284000000000,"is_new":false},{"rank":21,"model_id":"deepseek-v3.2","model_name":"DeepSeek-V3.2","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.702,"normalized_score":0.702,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-12-01","announcement_date":"2025-12-01","multimodal":false,"param_count":685000000000,"is_new":false},{"rank":22,"model_id":"deepseek-reasoner","model_name":"DeepSeek-V3.2 (Thinking)","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.702,"normalized_score":0.702,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-12-01","announcement_date":"2025-12-01","multimodal":false,"param_count":685000000000,"is_new":false},{"rank":23,"model_id":"qwen3.5-397b-a17b","model_name":"Qwen3.5-397B-A17B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.693,"normalized_score":0.693,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-02-16","announcement_date":"2026-02-16","multimodal":true,"param_count":397000000000,"is_new":false},{"rank":24,"model_id":"nemotron-3-ultra-550b-a55b","model_name":"Nemotron 3 Ultra (550B A55B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.677,"normalized_score":0.677,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-06-04","announcement_date":"2026-06-04","multimodal":false,"param_count":550000000000,"is_new":false},{"rank":25,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.672,"normalized_score":0.672,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-04-16","announcement_date":"2026-04-16","multimodal":true,"param_count":35000000000,"is_new":false},{"rank":26,"model_id":"glm-4.7","model_name":"GLM-4.7","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.667,"normalized_score":0.667,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-12-22","announcement_date":"2025-12-22","multimodal":true,"param_count":358000000000,"is_new":false},{"rank":27,"model_id":"mai-code-1-flash","model_name":"MAI-Code-1-Flash","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.655,"normalized_score":0.655,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-06-02","announcement_date":"2026-06-02","multimodal":false,"param_count":null,"is_new":false},{"rank":28,"model_id":"laguna-xs-2.1","model_name":"Laguna XS 2.1","organization_name":"Poolside","organization_id":"poolside","benchmark_score":0.631,"normalized_score":0.631,"verified":false,"self_reported":true,"provider_id":"poolside","input_cost_per_million":0.1,"output_cost_per_million":0.2,"speed_rps":null,"context_window":262144,"release_date":"2026-07-02","announcement_date":"2026-07-02","multimodal":false,"param_count":33000000000,"is_new":false},{"rank":29,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.611,"normalized_score":0.611,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-09-05","announcement_date":"2025-09-05","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":30,"model_id":"deepseek-v3.2-exp","model_name":"DeepSeek-V3.2-Exp","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.579,"normalized_score":0.579,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-09-29","announcement_date":"2025-09-29","multimodal":false,"param_count":685000000000,"is_new":false},{"rank":31,"model_id":"minimax-m2","model_name":"MiniMax M2","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.565,"normalized_score":0.565,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":204800,"release_date":"2025-10-27","announcement_date":"2025-10-27","multimodal":false,"param_count":230000000000,"is_new":false},{"rank":32,"model_id":"qwen3-coder-480b-a35b-instruct","model_name":"Qwen3-Coder 480B A35B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.547,"normalized_score":0.547,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-01-31","announcement_date":"2025-01-31","multimodal":false,"param_count":480000000000,"is_new":false},{"rank":33,"model_id":"deepseek-v3.1","model_name":"DeepSeek-V3.1","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.545,"normalized_score":0.545,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-01-10","announcement_date":"2025-01-10","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":34,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.473,"normalized_score":0.473,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-09-05","announcement_date":"2025-09-05","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":35,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.473,"normalized_score":0.473,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-07-11","announcement_date":"2025-07-11","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":36,"model_id":"nemotron-3-super-120b-a12b","model_name":"Nemotron 3 Super (120B A12B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.4578,"normalized_score":0.4578,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-03-11","announcement_date":"2026-03-11","multimodal":false,"param_count":120000000000,"is_new":false},{"rank":37,"model_id":"nemotron-3.5-lightning-30b-a3b","model_name":"Nemotron 3.5 Lightning (30B A3B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.3933,"normalized_score":0.3933,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.05,"output_cost_per_million":0.2,"speed_rps":null,"context_window":262144,"release_date":"2026-08-11","announcement_date":"2026-08-11","multimodal":false,"param_count":30000000000,"is_new":false},{"rank":38,"model_id":"longcat-flash-lite","model_name":"LongCat-Flash-Lite","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.381,"normalized_score":0.381,"verified":false,"self_reported":true,"provider_id":"meituan","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":500.0,"context_window":256000,"release_date":"2026-02-05","announcement_date":"2026-02-05","multimodal":false,"param_count":68500000000,"is_new":false},{"rank":39,"model_id":"deepseek-r1-0528","model_name":"DeepSeek-R1-0528","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.305,"normalized_score":0.305,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-05-28","announcement_date":"2025-05-28","multimodal":false,"param_count":671000000000,"is_new":false}]}