{"benchmark_id":"codeforces","benchmark_name":"CodeForces","benchmark_description":"A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic problems with difficulty ratings ranging from 800 to 2400. Problems cover diverse algorithmic categories including dynamic programming, graph algorithms, data structures, and mathematical problems with standardized evaluation through direct platform submission.","max_score":3000.0,"categories":["math","reasoning"],"modality":"text","total_models":17,"entries":[{"rank":1,"model_id":"deepseek-v4-pro-max","model_name":"DeepSeek-V4-Pro-Max","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":1.0,"normalized_score":1.0,"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":2,"model_id":"deepseek-v4-flash-max","model_name":"DeepSeek-V4-Flash-Max","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":1.0,"normalized_score":1.0,"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":3,"model_id":"deepseek-v4-flash-0423","model_name":"DeepSeek-V4-Flash-0423","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.9387,"normalized_score":0.9387,"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":4,"model_id":"deepseek-v3.2-speciale","model_name":"DeepSeek-V3.2-Speciale","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.9,"normalized_score":0.9,"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":5,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.851,"normalized_score":0.851,"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":"2026-02-24","announcement_date":"2026-02-24","multimodal":true,"param_count":122000000000,"is_new":false},{"rank":6,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.822,"normalized_score":0.822,"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":"2026-02-24","announcement_date":"2026-02-24","multimodal":true,"param_count":35000000000,"is_new":false},{"rank":7,"model_id":"gpt-oss-120b","model_name":"GPT OSS 120B","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.821,"normalized_score":0.821,"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":"2025-08-05","announcement_date":"2025-08-05","multimodal":false,"param_count":116800000000,"is_new":false},{"rank":8,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.807,"normalized_score":0.807,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":2.4,"speed_rps":null,"context_window":262144,"release_date":"2026-02-24","announcement_date":"2026-02-24","multimodal":true,"param_count":27000000000,"is_new":false},{"rank":9,"model_id":"deepseek-v3.2","model_name":"DeepSeek-V3.2","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.795,"normalized_score":0.795,"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":10,"model_id":"deepseek-reasoner","model_name":"DeepSeek-V3.2 (Thinking)","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.795,"normalized_score":0.795,"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":11,"model_id":"gpt-oss-20b","model_name":"GPT OSS 20B","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.7433,"normalized_score":0.7433,"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":"2025-08-05","announcement_date":"2025-08-05","multimodal":false,"param_count":20900000000,"is_new":false},{"rank":12,"model_id":"deepseek-v3.2-exp","model_name":"DeepSeek-V3.2-Exp","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.707,"normalized_score":0.707,"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":13,"model_id":"deepseek-v3.1","model_name":"DeepSeek-V3.1","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.697,"normalized_score":0.697,"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":14,"model_id":"qwen3-32b","model_name":"Qwen3 32B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.659,"normalized_score":0.659,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.3,"speed_rps":26.95,"context_window":128000,"release_date":"2025-04-29","announcement_date":"2025-04-29","multimodal":false,"param_count":32800000000,"is_new":false},{"rank":15,"model_id":"deepseek-r1-0528","model_name":"DeepSeek-R1-0528","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.6433,"normalized_score":0.6433,"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},{"rank":16,"model_id":"gemma-4-12b-it","model_name":"Gemma 4 12B","organization_name":"Google","organization_id":"google","benchmark_score":0.553,"normalized_score":0.553,"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":"2026-05-23","announcement_date":"2026-05-23","multimodal":true,"param_count":11959730224,"is_new":false},{"rank":17,"model_id":"diffusiongemma-26b-a4b-it","model_name":"DiffusionGemma 26B-A4B","organization_name":"Google","organization_id":"google","benchmark_score":0.4763,"normalized_score":0.4763,"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":"2026-06-10","announcement_date":"2026-06-10","multimodal":true,"param_count":25200000000,"is_new":false}]}