{"benchmark_id":"livecodebench","benchmark_name":"LiveCodeBench","benchmark_description":"LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.","max_score":1.0,"categories":["reasoning","general","code"],"modality":"text","total_models":75,"entries":[{"rank":1,"model_id":"deepseek-v4-pro-max","model_name":"DeepSeek-V4-Pro-Max","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.935,"normalized_score":0.935,"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":0.916,"normalized_score":0.916,"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":0.884,"normalized_score":0.884,"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":"solar-pro4","model_name":"Solar Pro 4","organization_name":"Upstage","organization_id":"upstage","benchmark_score":0.878,"normalized_score":0.878,"verified":false,"self_reported":true,"provider_id":"upstage","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":524288,"release_date":"2026-08-06","announcement_date":"2026-08-06","multimodal":false,"param_count":null,"is_new":false},{"rank":5,"model_id":"deepseek-v3.2","model_name":"DeepSeek-V3.2","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.833,"normalized_score":0.833,"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":6,"model_id":"deepseek-reasoner","model_name":"DeepSeek-V3.2 (Thinking)","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.833,"normalized_score":0.833,"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":7,"model_id":"minimax-m2","model_name":"MiniMax M2","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.83,"normalized_score":0.83,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":204800,"release_date":"2025-10-27","announcement_date":"2025-10-27","multimodal":false,"param_count":230000000000,"is_new":false},{"rank":8,"model_id":"longcat-flash-thinking-2601","model_name":"LongCat-Flash-Thinking-2601","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.828,"normalized_score":0.828,"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":"2026-01-14","announcement_date":"2026-01-14","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":9,"model_id":"nemotron-3-super-120b-a12b","model_name":"Nemotron 3 Super (120B A12B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.8119,"normalized_score":0.8119,"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":"2026-03-11","announcement_date":"2026-03-11","multimodal":false,"param_count":120000000000,"is_new":false},{"rank":10,"model_id":"grok-3-mini","model_name":"Grok-3 Mini","organization_name":"xAI","organization_id":"xai","benchmark_score":0.804,"normalized_score":0.804,"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":"2025-02-17","announcement_date":"2025-02-17","multimodal":true,"param_count":null,"is_new":false},{"rank":11,"model_id":"grok-4-fast","model_name":"Grok 4 Fast","organization_name":"xAI","organization_id":"xai","benchmark_score":0.8,"normalized_score":0.8,"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":"2025-08-28","announcement_date":"2025-08-28","multimodal":true,"param_count":null,"is_new":false},{"rank":12,"model_id":"longcat-flash-thinking","model_name":"LongCat-Flash-Thinking","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.794,"normalized_score":0.794,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":13,"model_id":"grok-4-heavy","model_name":"Grok-4 Heavy","organization_name":"xAI","organization_id":"xai","benchmark_score":0.794,"normalized_score":0.794,"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":null,"announcement_date":"2025-07-09","multimodal":true,"param_count":null,"is_new":false},{"rank":14,"model_id":"grok-3","model_name":"Grok-3","organization_name":"xAI","organization_id":"xai","benchmark_score":0.794,"normalized_score":0.794,"verified":false,"self_reported":true,"provider_id":"xai","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":100.0,"context_window":128000,"release_date":"2025-02-17","announcement_date":"2025-02-17","multimodal":true,"param_count":null,"is_new":false},{"rank":15,"model_id":"grok-4","model_name":"Grok-4","organization_name":"xAI","organization_id":"xai","benchmark_score":0.79,"normalized_score":0.79,"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":"2025-07-09","announcement_date":"2025-07-09","multimodal":true,"param_count":null,"is_new":false},{"rank":16,"model_id":"minimax-m2.1","model_name":"MiniMax M2.1","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.78,"normalized_score":0.78,"verified":false,"self_reported":true,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":100.0,"context_window":1000000,"release_date":"2025-12-23","announcement_date":"2025-12-23","multimodal":false,"param_count":230000000000,"is_new":false},{"rank":17,"model_id":"nova-2-pro","model_name":"Nova 2 Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.746,"normalized_score":0.746,"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":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false},{"rank":18,"model_id":"deepseek-v3.2-exp","model_name":"DeepSeek-V3.2-Exp","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.741,"normalized_score":0.741,"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":19,"model_id":"deepseek-r1-0528","model_name":"DeepSeek-R1-0528","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.733,"normalized_score":0.733,"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":20,"model_id":"glm-4.5","model_name":"GLM-4.5","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.729,"normalized_score":0.729,"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":"2025-07-28","announcement_date":"2025-07-28","multimodal":false,"param_count":355000000000,"is_new":false},{"rank":21,"model_id":"nvidia-nemotron-nano-9b-v2","model_name":"Nemotron Nano 9B v2","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.711,"normalized_score":0.711,"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":"2025-08-18","announcement_date":"2025-08-18","multimodal":false,"param_count":8900000000,"is_new":false},{"rank":22,"model_id":"nova-2-lite","model_name":"Nova 2 Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.71,"normalized_score":0.71,"verified":false,"self_reported":true,"provider_id":"bedrock","input_cost_per_million":0.3,"output_cost_per_million":2.5,"speed_rps":null,"context_window":1000000,"release_date":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false},{"rank":23,"model_id":"glm-4.5-air","model_name":"GLM-4.5-Air","organization_name":"Zhipu AI","organization_id":"zai-org","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":"2025-07-28","announcement_date":"2025-07-28","multimodal":false,"param_count":106000000000,"is_new":false},{"rank":24,"model_id":"qwen3-235b-a22b","model_name":"Qwen3 235B A22B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","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":"2025-04-29","announcement_date":"2025-04-29","multimodal":false,"param_count":235000000000,"is_new":false},{"rank":25,"model_id":"gemini-2.5-pro-preview-06-05","model_name":"Gemini 2.5 Pro Preview 06-05","organization_name":"Google","organization_id":"google","benchmark_score":0.69,"normalized_score":0.69,"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":"2025-06-05","announcement_date":"2025-06-05","multimodal":true,"param_count":null,"is_new":false},{"rank":26,"model_id":"mercury-2","model_name":"Mercury 2","organization_name":"Inception","organization_id":"inceptionlabs","benchmark_score":0.67,"normalized_score":0.67,"verified":false,"self_reported":true,"provider_id":"inception","input_cost_per_million":0.25,"output_cost_per_million":0.75,"speed_rps":1009.0,"context_window":128000,"release_date":"2026-02-24","announcement_date":"2026-02-24","multimodal":false,"param_count":null,"is_new":false},{"rank":27,"model_id":"llama-3.1-nemotron-ultra-253b-v1","model_name":"Llama 3.1 Nemotron Ultra 253B v1","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.6631,"normalized_score":0.6631,"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":"2025-04-07","announcement_date":"2025-04-07","multimodal":false,"param_count":253000000000,"is_new":false},{"rank":28,"model_id":"qwen3-32b","model_name":"Qwen3 32B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.657,"normalized_score":0.657,"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":29,"model_id":"minimax-m1-80k","model_name":"MiniMax M1 80K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.65,"normalized_score":0.65,"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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false},{"rank":30,"model_id":"ministral-14b-latest","model_name":"Ministral 3 (14B Reasoning 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.646,"normalized_score":0.646,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":14000000000,"is_new":false},{"rank":31,"model_id":"mistral-small-latest","model_name":"Mistral Small 4","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.636,"normalized_score":0.636,"verified":false,"self_reported":true,"provider_id":"mistral","input_cost_per_million":0.15,"output_cost_per_million":0.6,"speed_rps":null,"context_window":256000,"release_date":"2026-03-16","announcement_date":"2026-03-16","multimodal":true,"param_count":119000000000,"is_new":false},{"rank":32,"model_id":"qwq-32b","model_name":"QwQ-32B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.634,"normalized_score":0.634,"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":"2025-03-05","announcement_date":"2025-03-05","multimodal":false,"param_count":32500000000,"is_new":false},{"rank":33,"model_id":"qwen3-30b-a3b","model_name":"Qwen3 30B A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.626,"normalized_score":0.626,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.3,"speed_rps":82.57,"context_window":128000,"release_date":"2025-04-29","announcement_date":"2025-04-29","multimodal":false,"param_count":30500000000,"is_new":false},{"rank":34,"model_id":"minimax-m1-40k","model_name":"MiniMax M1 40K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.623,"normalized_score":0.623,"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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false},{"rank":35,"model_id":"ministral-8b-latest","model_name":"Ministral 3 (8B Reasoning 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.616,"normalized_score":0.616,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":36,"model_id":"deepseek-r1-distill-llama-70b","model_name":"DeepSeek R1 Distill Llama 70B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.575,"normalized_score":0.575,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":70600000000,"is_new":false},{"rank":37,"model_id":"deepseek-r1-distill-qwen-32b","model_name":"DeepSeek R1 Distill Qwen 32B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.572,"normalized_score":0.572,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":32800000000,"is_new":false},{"rank":38,"model_id":"deepseek-v3.1","model_name":"DeepSeek-V3.1","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.564,"normalized_score":0.564,"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":39,"model_id":"qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.555,"normalized_score":0.555,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":72700000000,"is_new":false},{"rank":40,"model_id":"ministral-3b-latest","model_name":"Min  istral 3 (3B Reasoning 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.548,"normalized_score":0.548,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":3000000000,"is_new":false},{"rank":41,"model_id":"phi-4-reasoning","model_name":"Phi 4 Reasoning","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.538,"normalized_score":0.538,"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":"2025-04-30","announcement_date":"2025-04-30","multimodal":false,"param_count":14000000000,"is_new":false},{"rank":42,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.537,"normalized_score":0.537,"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":"2025-09-05","announcement_date":"2025-09-05","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":43,"model_id":"phi-4-reasoning-plus","model_name":"Phi 4 Reasoning Plus","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.531,"normalized_score":0.531,"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":"2025-04-30","announcement_date":"2025-04-30","multimodal":false,"param_count":14000000000,"is_new":false},{"rank":44,"model_id":"deepseek-r1-distill-qwen-14b","model_name":"DeepSeek R1 Distill Qwen 14B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.531,"normalized_score":0.531,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":14800000000,"is_new":false},{"rank":45,"model_id":"magistral-small-2506","model_name":"Magistral Small 2506","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.513,"normalized_score":0.513,"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":"2025-06-10","announcement_date":"2025-06-10","multimodal":false,"param_count":24000000000,"is_new":false},{"rank":46,"model_id":"magistral-medium","model_name":"Magistral Medium","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.503,"normalized_score":0.503,"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":"2025-06-10","announcement_date":"2025-06-10","multimodal":true,"param_count":24000000000,"is_new":false},{"rank":47,"model_id":"deepseek-r1-zero","model_name":"DeepSeek R1 Zero","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.5,"normalized_score":0.5,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":48,"model_id":"qwq-32b-preview","model_name":"QwQ-32B-Preview","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.5,"normalized_score":0.5,"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":"2024-11-28","announcement_date":"2024-11-28","multimodal":false,"param_count":32500000000,"is_new":false},{"rank":49,"model_id":"deepseek-v3-0324","model_name":"DeepSeek-V3 0324","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.492,"normalized_score":0.492,"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":"2025-03-25","announcement_date":"2025-03-25","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":50,"model_id":"longcat-flash-chat","model_name":"LongCat-Flash-Chat","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.4802,"normalized_score":0.4802,"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":"2025-08-29","announcement_date":"2025-08-29","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":51,"model_id":"llama-4-maverick","model_name":"Llama 4 Maverick","organization_name":"Meta","organization_id":"meta","benchmark_score":0.434,"normalized_score":0.434,"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":"2025-04-05","announcement_date":"2025-04-05","multimodal":true,"param_count":400000000000,"is_new":false},{"rank":52,"model_id":"deepseek-r1-distill-llama-8b","model_name":"DeepSeek R1 Distill Llama 8B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.396,"normalized_score":0.396,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":8030000000,"is_new":false},{"rank":53,"model_id":"deepseek-r1-distill-qwen-7b","model_name":"DeepSeek R1 Distill Qwen 7B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.376,"normalized_score":0.376,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":7620000000,"is_new":false},{"rank":54,"model_id":"deepseek-v3","model_name":"DeepSeek-V3","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.376,"normalized_score":0.376,"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":"2024-12-25","announcement_date":"2024-12-25","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":55,"model_id":"gemini-2.0-flash","model_name":"Gemini 2.0 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.351,"normalized_score":0.351,"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":"2024-12-01","announcement_date":"2024-12-01","multimodal":true,"param_count":null,"is_new":false},{"rank":56,"model_id":"mistral-large-3-675B-instruct-2512-eagle","model_name":"Mistral Large 3 (675B Instruct 2512 Eagle)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.344,"normalized_score":0.344,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":675000000000,"is_new":false},{"rank":57,"model_id":"mistral-large-3-675b-instruct-2512-nvfp4","model_name":"Mistral Large 3 (675B Instruct 2512 NVFP4)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.344,"normalized_score":0.344,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":675000000000,"is_new":false},{"rank":58,"model_id":"mistral-large-latest","model_name":"Mistral Large 3 (675B Instruct 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.344,"normalized_score":0.344,"verified":false,"self_reported":true,"provider_id":"mistral","input_cost_per_million":0.5,"output_cost_per_million":1.5,"speed_rps":45.89,"context_window":262100,"release_date":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":675000000000,"is_new":false},{"rank":59,"model_id":"mistral-large-3-675b-base-2512","model_name":"Mistral Large 3 (675B Base)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.344,"normalized_score":0.344,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":675000000000,"is_new":false},{"rank":60,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.337,"normalized_score":0.337,"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":"2025-06-17","announcement_date":"2025-06-17","multimodal":true,"param_count":null,"is_new":false},{"rank":61,"model_id":"llama-4-scout","model_name":"Llama 4 Scout","organization_name":"Meta","organization_id":"meta","benchmark_score":0.328,"normalized_score":0.328,"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":"2025-04-05","announcement_date":"2025-04-05","multimodal":true,"param_count":109000000000,"is_new":false},{"rank":62,"model_id":"qwen-2.5-coder-32b-instruct","model_name":"Qwen2.5-Coder 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.314,"normalized_score":0.314,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":32000000000,"is_new":false},{"rank":63,"model_id":"gemini-diffusion","model_name":"Gemini Diffusion","organization_name":"Google","organization_id":"google","benchmark_score":0.309,"normalized_score":0.309,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":false,"param_count":null,"is_new":false},{"rank":64,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_name":"Google","organization_id":"google","benchmark_score":0.297,"normalized_score":0.297,"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":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":27000000000,"is_new":false},{"rank":65,"model_id":"qwen-2.5-7b-instruct","model_name":"Qwen2.5 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.287,"normalized_score":0.287,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":7610000000,"is_new":false},{"rank":66,"model_id":"qwen2-7b-instruct","model_name":"Qwen2 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.266,"normalized_score":0.266,"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":"2024-07-23","announcement_date":"2024-07-23","multimodal":false,"param_count":7620000000,"is_new":false},{"rank":67,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_name":"Google","organization_id":"google","benchmark_score":0.246,"normalized_score":0.246,"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":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":12000000000,"is_new":false},{"rank":68,"model_id":"qwen-2.5-coder-7b-instruct","model_name":"Qwen2.5-Coder 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.182,"normalized_score":0.182,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":7000000000,"is_new":false},{"rank":69,"model_id":"deepseek-r1-distill-qwen-1.5b","model_name":"DeepSeek R1 Distill Qwen 1.5B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.169,"normalized_score":0.169,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":1780000000,"is_new":false},{"rank":70,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.132,"normalized_score":0.132,"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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":71,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.132,"normalized_score":0.132,"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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":72,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_name":"Google","organization_id":"google","benchmark_score":0.132,"normalized_score":0.132,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false},{"rank":73,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_name":"Google","organization_id":"google","benchmark_score":0.132,"normalized_score":0.132,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false},{"rank":74,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_name":"Google","organization_id":"google","benchmark_score":0.126,"normalized_score":0.126,"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":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":4000000000,"is_new":false},{"rank":75,"model_id":"gemma-3-1b-it","model_name":"Gemma 3 1B","organization_name":"Google","organization_id":"google","benchmark_score":0.019,"normalized_score":0.019,"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":"2025-03-12","announcement_date":"2025-03-12","multimodal":false,"param_count":1000000000,"is_new":false}]}