{"benchmark_id":"ojbench","name":"OJBench","parent_benchmark":null,"categories":["reasoning"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"OJBench is a competition-level code benchmark designed to assess the competitive-level code reasoning abilities of large language models. It comprises 232 programming competition problems from NOI and ICPC, categorized into Easy, Medium, and Hard difficulty levels. The benchmark evaluates models' ability to solve complex competitive programming challenges using Python and C++.","paper_link":"https://arxiv.org/abs/2506.16395","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.502814+00:00","updated_at":"2026-07-05T18:27:57.480960+00:00","statistics":{"total_models":9,"average_score":0.37922222222222224,"min_score":0.271,"max_score":0.606,"score_stddev":0.11026193560991229,"verified_count":0,"self_reported_count":9},"child_benchmarks":[{"benchmark_id":"ojbench-cpp","name":"OJBench (C++)","categories":["reasoning","code"],"modality":"text","max_score":1.0,"description":"OJBench (C++) is the C++ subset of OJBench, a competition-level code benchmark that evaluates large language models on programming competition problems from NOI and ICPC using C++ as the implementation language."}],"linked_dataset":null,"models":[{"rank":1,"model_id":"kimi-k2.6","model_name":"Kimi K2.6","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.606,"normalized_score":0.606,"verified":false,"self_reported":true,"self_reported_source":"https://www.kimi.com/blog/kimi-k2-6","analysis_method":"Python","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.75,"output_cost_per_million":3.5,"context_window":262144,"announcement_date":"2026-04-20","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Together"},{"rank":2,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.487,"normalized_score":0.487,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/thinking.html","analysis_method":"cpp, no 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":3,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.401,"normalized_score":0.401,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":2.4,"context_window":262144,"announcement_date":"2026-02-24","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":4,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.395,"normalized_score":0.395,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":122000000000,"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":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.36,"normalized_score":0.36,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","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},{"rank":6,"model_id":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3-235B-A22B-Thinking-2507","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.325,"normalized_score":0.325,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-thinking/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-07-25","param_count":235000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":7,"model_id":"qwen3-next-80b-a3b-thinking","model_name":"Qwen3-Next-80B-A3B-Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.297,"normalized_score":0.297,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-next/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-10","param_count":80000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.271,"normalized_score":0.271,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","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":"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":8,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.271,"normalized_score":0.271,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","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":"2025-07-11","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}]}