{"benchmark_id":"aider-polyglot-edit","benchmark_name":"Aider-Polyglot Edit","benchmark_description":"A challenging multi-language coding benchmark that evaluates models' code editing abilities across C++, Go, Java, JavaScript, Python, and Rust. Contains 225 of Exercism's most difficult programming problems, selected as problems that were solved by 3 or fewer out of 7 top coding models. The benchmark focuses on code editing tasks and measures both correctness of solutions and proper edit format usage. Designed to re-calibrate evaluation scales so top models score between 5-50%.","max_score":1.0,"categories":["general","code"],"modality":"text","total_models":10,"entries":[{"rank":1,"model_id":"deepseek-v3","model_name":"DeepSeek-V3","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.797,"normalized_score":0.797,"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":"2024-12-25","announcement_date":"2024-12-25","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":2,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.727,"normalized_score":0.727,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":85.0,"context_window":1048576,"release_date":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"o3-mini","model_name":"o3-mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.604,"normalized_score":0.604,"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":"2025-01-30","announcement_date":"2025-01-30","multimodal":false,"param_count":null,"is_new":false},{"rank":4,"model_id":"o4-mini","model_name":"o4-mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.582,"normalized_score":0.582,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":null,"is_new":false},{"rank":5,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.567,"normalized_score":0.567,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"gpt-4.1-2025-04-14","model_name":"GPT-4.1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.529,"normalized_score":0.529,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":2.0,"output_cost_per_million":8.0,"speed_rps":100.0,"context_window":1047576,"release_date":"2025-04-14","announcement_date":"2025-04-14","multimodal":true,"param_count":null,"is_new":false},{"rank":7,"model_id":"gpt-4.5","model_name":"GPT-4.5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.449,"normalized_score":0.449,"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":"2025-02-27","announcement_date":"2025-02-27","multimodal":true,"param_count":null,"is_new":false},{"rank":8,"model_id":"gpt-4.1-mini-2025-04-14","model_name":"GPT-4.1 mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.316,"normalized_score":0.316,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":0.4,"output_cost_per_million":1.6,"speed_rps":150.0,"context_window":1047576,"release_date":"2025-04-14","announcement_date":"2025-04-14","multimodal":true,"param_count":null,"is_new":false},{"rank":9,"model_id":"gpt-4o-2024-08-06","model_name":"GPT-4o","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.182,"normalized_score":0.182,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":10.0,"speed_rps":132.0,"context_window":128000,"release_date":"2024-08-06","announcement_date":"2024-08-06","multimodal":true,"param_count":null,"is_new":false},{"rank":10,"model_id":"gpt-4.1-nano-2025-04-14","model_name":"GPT-4.1 nano","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.062,"normalized_score":0.062,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":200.0,"context_window":1047576,"release_date":"2025-04-14","announcement_date":"2025-04-14","multimodal":true,"param_count":null,"is_new":false}]}