{"benchmark_id":"frontiercode-1.1","benchmark_name":"FrontierCode 1.1","benchmark_description":"FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.","max_score":1.0,"categories":["reasoning","agents","code"],"modality":"text","total_models":16,"entries":[{"rank":1,"model_id":"claude-fable-5","model_name":"Claude Fable 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.535,"normalized_score":0.535,"verified":false,"self_reported":false,"provider_id":"anthropic","input_cost_per_million":10.0,"output_cost_per_million":50.0,"speed_rps":null,"context_window":1000000,"release_date":"2026-06-09","announcement_date":"2026-06-09","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"claude-opus-5","model_name":"Claude Opus 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.534,"normalized_score":0.534,"verified":false,"self_reported":false,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":null,"context_window":1000000,"release_date":"2026-07-24","announcement_date":"2026-07-24","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"gpt-5.6-sol","model_name":"GPT-5.6 Sol","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.475,"normalized_score":0.475,"verified":false,"self_reported":false,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"speed_rps":null,"context_window":1050000,"release_date":"2026-07-09","announcement_date":"2026-07-09","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"claude-opus-4-8","model_name":"Claude Opus 4.8","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.465,"normalized_score":0.465,"verified":false,"self_reported":false,"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":5,"model_id":"gemini-3.7-flash","model_name":"Gemini 3.7 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.436,"normalized_score":0.436,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":0.75,"output_cost_per_million":3.75,"speed_rps":null,"context_window":1048576,"release_date":"2026-08-13","announcement_date":"2026-08-13","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"gpt-5.5","model_name":"GPT-5.5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.43,"normalized_score":0.43,"verified":false,"self_reported":false,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"speed_rps":null,"context_window":1050000,"release_date":"2026-04-23","announcement_date":"2026-04-23","multimodal":true,"param_count":null,"is_new":false},{"rank":7,"model_id":"claude-sonnet-5","model_name":"Claude Sonnet 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.427,"normalized_score":0.427,"verified":false,"self_reported":false,"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":8,"model_id":"grok-4.5","model_name":"Grok 4.5","organization_name":"xAI","organization_id":"xai","benchmark_score":0.424,"normalized_score":0.424,"verified":false,"self_reported":false,"provider_id":"xai","input_cost_per_million":2.0,"output_cost_per_million":6.0,"speed_rps":80.0,"context_window":500000,"release_date":"2026-07-16","announcement_date":"2026-07-16","multimodal":true,"param_count":null,"is_new":false},{"rank":9,"model_id":"gpt-5.6-terra","model_name":"GPT-5.6 Terra","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.413,"normalized_score":0.413,"verified":false,"self_reported":false,"provider_id":"openai","input_cost_per_million":2.0,"output_cost_per_million":12.0,"speed_rps":null,"context_window":1050000,"release_date":"2026-07-09","announcement_date":"2026-07-09","multimodal":true,"param_count":null,"is_new":false},{"rank":10,"model_id":"gpt-5.6-luna","model_name":"GPT-5.6 Luna","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.398,"normalized_score":0.398,"verified":false,"self_reported":false,"provider_id":"openai","input_cost_per_million":0.2,"output_cost_per_million":1.2,"speed_rps":null,"context_window":1050000,"release_date":"2026-07-09","announcement_date":"2026-07-09","multimodal":true,"param_count":null,"is_new":false},{"rank":11,"model_id":"claude-opus-4-7","model_name":"Claude Opus 4.7","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.385,"normalized_score":0.385,"verified":false,"self_reported":false,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-04-16","announcement_date":"2026-04-16","multimodal":true,"param_count":null,"is_new":false},{"rank":12,"model_id":"kimi-k2.7-code","model_name":"Kimi K2.7 Code","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.301,"normalized_score":0.301,"verified":false,"self_reported":false,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-06-12","announcement_date":"2026-06-12","multimodal":true,"param_count":1000000000000,"is_new":false},{"rank":13,"model_id":"glm-5.2","model_name":"GLM-5.2","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.245,"normalized_score":0.245,"verified":false,"self_reported":false,"provider_id":"deepinfra","input_cost_per_million":0.95,"output_cost_per_million":3.0,"speed_rps":null,"context_window":1048576,"release_date":"2026-06-16","announcement_date":"2026-06-16","multimodal":false,"param_count":753000000000,"is_new":false},{"rank":14,"model_id":"deepseek-v4-pro-max","model_name":"DeepSeek-V4-Pro-Max","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.176,"normalized_score":0.176,"verified":false,"self_reported":false,"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":15,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.147,"normalized_score":0.147,"verified":false,"self_reported":false,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":1000000,"release_date":"2026-06-01","announcement_date":"2026-06-01","multimodal":true,"param_count":428000000000,"is_new":false},{"rank":16,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.102,"normalized_score":0.102,"verified":false,"self_reported":false,"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}]}