{"benchmark_id":"deepswe-1.1","benchmark_name":"DeepSWE 1.1","benchmark_description":"DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":27,"entries":[{"rank":1,"model_id":"gpt-5.6-sol","model_name":"GPT-5.6 Sol","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.73,"normalized_score":0.73,"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":2,"model_id":"gpt-5.6-terra","model_name":"GPT-5.6 Terra","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.7,"normalized_score":0.7,"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":3,"model_id":"claude-fable-5","model_name":"Claude Fable 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.7,"normalized_score":0.7,"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":4,"model_id":"kimi-k3","model_name":"Kimi K3","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.69,"normalized_score":0.69,"verified":false,"self_reported":false,"provider_id":"novita","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-16","announcement_date":"2026-07-16","multimodal":true,"param_count":2800000000000,"is_new":false},{"rank":5,"model_id":"claude-opus-5","model_name":"Claude Opus 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.688,"normalized_score":0.688,"verified":false,"self_reported":true,"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":6,"model_id":"gpt-5.6-luna","model_name":"GPT-5.6 Luna","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.67,"normalized_score":0.67,"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":7,"model_id":"gpt-5.5","model_name":"GPT-5.5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.67,"normalized_score":0.67,"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":8,"model_id":"glm-5.3","model_name":"GLM-5.3","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.669,"normalized_score":0.669,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":1.4,"output_cost_per_million":4.4,"speed_rps":null,"context_window":1048576,"release_date":"2026-08-14","announcement_date":"2026-08-14","multimodal":false,"param_count":753000000000,"is_new":false},{"rank":9,"model_id":"grok-4.6","model_name":"Grok 4.6","organization_name":"xAI","organization_id":"xai","benchmark_score":0.659,"normalized_score":0.659,"verified":false,"self_reported":true,"provider_id":"xai","input_cost_per_million":2.0,"output_cost_per_million":6.0,"speed_rps":null,"context_window":500000,"release_date":"2026-08-12","announcement_date":"2026-08-12","multimodal":true,"param_count":null,"is_new":false},{"rank":10,"model_id":"gemini-3.7-flash","model_name":"Gemini 3.7 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.653,"normalized_score":0.653,"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":11,"model_id":"glm-5.3-flash","model_name":"GLM-5.3-Flash","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.634,"normalized_score":0.634,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.15,"output_cost_per_million":0.5,"speed_rps":null,"context_window":1048576,"release_date":"2026-08-26","announcement_date":"2026-08-26","multimodal":true,"param_count":320000000000,"is_new":true},{"rank":12,"model_id":"muse-spark-1.2","model_name":"Muse Spark 1.2","organization_name":"Meta","organization_id":"meta","benchmark_score":0.593,"normalized_score":0.593,"verified":false,"self_reported":true,"provider_id":"meta","input_cost_per_million":0.1,"output_cost_per_million":0.2,"speed_rps":null,"context_window":1048576,"release_date":"2026-08-05","announcement_date":"2026-08-05","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"claude-opus-4-8","model_name":"Claude Opus 4.8","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.59,"normalized_score":0.59,"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":14,"model_id":"qwen3.8-flash-next","model_name":"Qwen3.8-Flash-Next","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.587,"normalized_score":0.587,"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":"2026-08-26","announcement_date":"2026-08-26","multimodal":true,"param_count":125000000000,"is_new":true},{"rank":15,"model_id":"qwen3.8-max","model_name":"Qwen3.8 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.566,"normalized_score":0.566,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":1.65,"output_cost_per_million":4.951,"speed_rps":null,"context_window":256000,"release_date":"2026-08-02","announcement_date":"2026-08-02","multimodal":true,"param_count":2400000000000,"is_new":false},{"rank":16,"model_id":"grok-4.5","model_name":"Grok 4.5","organization_name":"xAI","organization_id":"xai","benchmark_score":0.54,"normalized_score":0.54,"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":17,"model_id":"claude-sonnet-5","model_name":"Claude Sonnet 5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.54,"normalized_score":0.54,"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":18,"model_id":"muse-spark-1.1","model_name":"Muse Spark 1.1","organization_name":"Meta","organization_id":"meta","benchmark_score":0.53,"normalized_score":0.53,"verified":false,"self_reported":false,"provider_id":"meta","input_cost_per_million":1.25,"output_cost_per_million":4.25,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-09","announcement_date":"2026-07-09","multimodal":true,"param_count":null,"is_new":false},{"rank":19,"model_id":"gpt-5.4","model_name":"GPT-5.4","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.52,"normalized_score":0.52,"verified":false,"self_reported":false,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":15.0,"speed_rps":50.0,"context_window":1000000,"release_date":"2026-03-05","announcement_date":"2026-03-05","multimodal":true,"param_count":null,"is_new":false},{"rank":20,"model_id":"gemini-3.6-flash","model_name":"Gemini 3.6 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.49,"normalized_score":0.49,"verified":false,"self_reported":false,"provider_id":"google","input_cost_per_million":1.5,"output_cost_per_million":7.5,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-21","announcement_date":"2026-07-21","multimodal":true,"param_count":null,"is_new":false},{"rank":21,"model_id":"glm-5.2","model_name":"GLM-5.2","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.44,"normalized_score":0.44,"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":22,"model_id":"qwen3.8-27b","model_name":"Qwen3.8-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.422,"normalized_score":0.422,"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":"2026-08-14","announcement_date":"2026-08-14","multimodal":true,"param_count":27781427952,"is_new":false},{"rank":23,"model_id":"laguna-s-2.1","model_name":"Laguna S 2.1","organization_name":"Poolside","organization_id":"poolside","benchmark_score":0.404,"normalized_score":0.404,"verified":false,"self_reported":true,"provider_id":"poolside","input_cost_per_million":0.1,"output_cost_per_million":0.2,"speed_rps":null,"context_window":1048576,"release_date":"2026-07-21","announcement_date":"2026-07-21","multimodal":false,"param_count":118000000000,"is_new":false},{"rank":24,"model_id":"gemini-3.5-flash","model_name":"Gemini 3.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.37,"normalized_score":0.37,"verified":false,"self_reported":false,"provider_id":"google","input_cost_per_million":1.5,"output_cost_per_million":9.0,"speed_rps":null,"context_window":1048576,"release_date":"2026-05-19","announcement_date":"2026-05-19","multimodal":true,"param_count":null,"is_new":false},{"rank":25,"model_id":"kimi-k2.7-code","model_name":"Kimi K2.7 Code","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.31,"normalized_score":0.31,"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":26,"model_id":"claude-sonnet-4-6","model_name":"Claude Sonnet 4.6","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.3,"normalized_score":0.3,"verified":false,"self_reported":false,"provider_id":"anthropic","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":42.0,"context_window":200000,"release_date":"2026-02-17","announcement_date":"2026-02-17","multimodal":true,"param_count":null,"is_new":false},{"rank":27,"model_id":"gemini-3.1-pro-preview","model_name":"Gemini 3.1 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.12,"normalized_score":0.12,"verified":false,"self_reported":false,"provider_id":"google","input_cost_per_million":2.5,"output_cost_per_million":15.0,"speed_rps":90.0,"context_window":1048576,"release_date":"2026-02-19","announcement_date":"2026-02-19","multimodal":true,"param_count":null,"is_new":false}]}