{"benchmark_id":"nl2repo","name":"NL2Repo","parent_benchmark":null,"categories":["agents","coding"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.369267+00:00","updated_at":"2026-07-17T06:43:05.754597+00:00","statistics":{"total_models":12,"average_score":0.41802500000000004,"min_score":0.294,"max_score":0.489,"score_stddev":0.054805343551684656,"verified_count":0,"self_reported_count":12},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"glm-5.2","model_name":"GLM-5.2","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.489,"normalized_score":0.489,"verified":false,"self_reported":true,"self_reported_source":"https://z.ai/blog/glm-5.2","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.95,"output_cost_per_million":3.0,"context_window":1048576,"announcement_date":"2026-06-16","param_count":753000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Fireworks","best_throughput":null,"throughput_provider":"Fireworks","context_provider":"DeepInfra"},{"rank":2,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.472,"normalized_score":0.472,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7","analysis_method":"Claude Code scaffold","verification_date":null,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"context_window":1000000,"announcement_date":"2026-05-19","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Together"},{"rank":3,"model_id":"seed-2.1-pro","model_name":"Seed 2.1 Pro","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.47,"normalized_score":0.47,"verified":false,"self_reported":true,"self_reported_source":"https://seed.bytedance.com/en/seed2_1","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-24","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"hy3","model_name":"Hy3","organization_id":"tencent","organization_name":"Tencent","organization_country":"CN","score":0.456,"normalized_score":0.456,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/tencent/Hy3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-07-06","param_count":295000000000,"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":"seed-2.1-turbo","model_name":"Seed 2.1 Turbo","organization_id":"bytedance","organization_name":"ByteDance","organization_country":"CN","score":0.437,"normalized_score":0.437,"verified":false,"self_reported":true,"self_reported_source":"https://seed.bytedance.com/en/seed2_1","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-24","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"glm-5.1","model_name":"GLM-5.1","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.427,"normalized_score":0.427,"verified":false,"self_reported":true,"self_reported_source":"https://z.ai/blog/glm-5.1","analysis_method":null,"verification_date":null,"provider_id":"friendli","input_cost_per_million":1.4,"output_cost_per_million":4.4,"context_window":200000,"announcement_date":"2026-04-07","param_count":754000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"FriendliAI","best_throughput":null,"throughput_provider":"FriendliAI","context_provider":"FriendliAI"},{"rank":7,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.4213,"normalized_score":0.4213,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/blog/minimax-m3","analysis_method":null,"verification_date":null,"provider_id":"fireworks","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2026-06-01","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Fireworks","best_throughput":null,"throughput_provider":"Fireworks","context_provider":"Novita"},{"rank":8,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.411,"normalized_score":0.411,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7-plus","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.32,"output_cost_per_million":1.28,"context_window":1000000,"announcement_date":"2026-05-31","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":9,"model_id":"minimax-m2.7","model_name":"MiniMax M2.7","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.398,"normalized_score":0.398,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/news/minimax-m27-en","analysis_method":null,"verification_date":null,"provider_id":"novita","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":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":10,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.379,"normalized_score":0.379,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.5,"output_cost_per_million":3.0,"context_window":1000000,"announcement_date":"2026-04-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":11,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.362,"normalized_score":0.362,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-27b","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"context_window":262144,"announcement_date":"2026-04-21","param_count":27781427952,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":12,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.294,"normalized_score":0.294,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-16","param_count":35000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}