{"benchmark_id":"mmmu","benchmark_name":"MMMU","benchmark_description":"MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.","max_score":1.0,"categories":["multimodal","reasoning","general","healthcare","vision"],"modality":"multimodal","total_models":64,"entries":[{"rank":1,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.86,"normalized_score":0.86,"verified":false,"self_reported":true,"provider_id":"together","input_cost_per_million":0.5,"output_cost_per_million":3.0,"speed_rps":null,"context_window":1000000,"release_date":"2026-03-31","announcement_date":"2026-04-02","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gpt-5.1-2025-11-13","model_name":"GPT-5.1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.854,"normalized_score":0.854,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":100.0,"context_window":400000,"release_date":"2025-11-13","announcement_date":"2025-11-13","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"gpt-5.1-thinking-2025-11-12","model_name":"GPT-5.1 Thinking","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.854,"normalized_score":0.854,"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":"2025-11-12","announcement_date":"2025-11-12","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"gpt-5.1-instant-2025-11-12","model_name":"GPT-5.1 Instant","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.854,"normalized_score":0.854,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":100.0,"context_window":400000,"release_date":"2025-11-12","announcement_date":"2025-11-12","multimodal":true,"param_count":null,"is_new":false},{"rank":5,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.842,"normalized_score":0.842,"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":"2025-08-07","announcement_date":"2025-08-07","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.839,"normalized_score":0.839,"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":7,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.829,"normalized_score":0.829,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"speed_rps":null,"context_window":262144,"release_date":"2026-04-21","announcement_date":"2026-04-21","multimodal":true,"param_count":27781427952,"is_new":false},{"rank":8,"model_id":"o3-2025-04-16","model_name":"o3","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.829,"normalized_score":0.829,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":null,"is_new":false},{"rank":9,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.823,"normalized_score":0.823,"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":10,"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":0.82,"normalized_score":0.82,"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":11,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.817,"normalized_score":0.817,"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":"2026-04-16","announcement_date":"2026-04-16","multimodal":true,"param_count":35000000000,"is_new":false},{"rank":12,"model_id":"o4-mini","model_name":"o4-mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.816,"normalized_score":0.816,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.814,"normalized_score":0.814,"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":14,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.797,"normalized_score":0.797,"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":null,"is_new":false},{"rank":15,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.796,"normalized_score":0.796,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":85.0,"context_window":1048576,"release_date":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":16,"model_id":"exaone-4.5-33b","model_name":"EXAONE 4.5 33B","organization_name":"LG AI Research","organization_id":"lg","benchmark_score":0.787,"normalized_score":0.787,"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":"2026-04-09","announcement_date":"2026-04-09","multimodal":true,"param_count":33000000000,"is_new":false},{"rank":17,"model_id":"step3-vl-10b","model_name":"Step3-VL-10B","organization_name":"StepFun","organization_id":"stepfun","benchmark_score":0.781,"normalized_score":0.781,"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":"2026-01-15","announcement_date":"2026-01-15","multimodal":true,"param_count":10000000000,"is_new":false},{"rank":18,"model_id":"grok-3","model_name":"Grok-3","organization_name":"xAI","organization_id":"xai","benchmark_score":0.78,"normalized_score":0.78,"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":19,"model_id":"o1-2024-12-17","model_name":"o1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.776,"normalized_score":0.776,"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":"2024-12-17","announcement_date":"2024-12-17","multimodal":false,"param_count":null,"is_new":false},{"rank":20,"model_id":"gemini-2.0-flash-thinking","model_name":"Gemini 2.0 Flash Thinking","organization_name":"Google","organization_id":"google","benchmark_score":0.754,"normalized_score":0.754,"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":"2025-01-21","announcement_date":"2025-01-21","multimodal":true,"param_count":null,"is_new":false},{"rank":21,"model_id":"gpt-4.5","model_name":"GPT-4.5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.752,"normalized_score":0.752,"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":"2025-02-27","announcement_date":"2025-02-27","multimodal":true,"param_count":null,"is_new":false},{"rank":22,"model_id":"command-a-plus-05-2026","model_name":"Command A+","organization_name":"Cohere","organization_id":"cohere","benchmark_score":0.751,"normalized_score":0.751,"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":"2026-05-20","announcement_date":"2026-05-20","multimodal":true,"param_count":218000000000,"is_new":false},{"rank":23,"model_id":"claude-3-7-sonnet-20250219","model_name":"Claude 3.7 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.75,"normalized_score":0.75,"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":"2025-02-24","announcement_date":"2025-02-24","multimodal":true,"param_count":null,"is_new":false},{"rank":24,"model_id":"gpt-4.1-2025-04-14","model_name":"GPT-4.1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.748,"normalized_score":0.748,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":2.0,"output_cost_per_million":8.0,"speed_rps":100.0,"context_window":1047576,"release_date":"2025-04-14","announcement_date":"2025-04-14","multimodal":true,"param_count":null,"is_new":false},{"rank":25,"model_id":"claude-sonnet-4-20250514","model_name":"Claude Sonnet 4","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.744,"normalized_score":0.744,"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":"2025-05-22","announcement_date":"2025-05-22","multimodal":true,"param_count":null,"is_new":false},{"rank":26,"model_id":"llama-4-maverick","model_name":"Llama 4 Maverick","organization_name":"Meta","organization_id":"meta","benchmark_score":0.734,"normalized_score":0.734,"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":27,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_name":"Google","organization_id":"google","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":"2025-06-17","announcement_date":"2025-06-17","multimodal":true,"param_count":null,"is_new":false},{"rank":28,"model_id":"gpt-4.1-mini-2025-04-14","model_name":"GPT-4.1 mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.727,"normalized_score":0.727,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":0.4,"output_cost_per_million":1.6,"speed_rps":150.0,"context_window":1047576,"release_date":"2025-04-14","announcement_date":"2025-04-14","multimodal":true,"param_count":null,"is_new":false},{"rank":29,"model_id":"gpt-4o-2024-08-06","model_name":"GPT-4o","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.722,"normalized_score":0.722,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":10.0,"speed_rps":132.0,"context_window":128000,"release_date":"2024-08-06","announcement_date":"2024-08-06","multimodal":true,"param_count":null,"is_new":false},{"rank":30,"model_id":"gemini-2.0-flash","model_name":"Gemini 2.0 Flash","organization_name":"Google","organization_id":"google","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":"2024-12-01","announcement_date":"2024-12-01","multimodal":true,"param_count":null,"is_new":false},{"rank":31,"model_id":"qvq-72b-preview","model_name":"QvQ-72B-Preview","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.703,"normalized_score":0.703,"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":true,"param_count":73400000000,"is_new":false},{"rank":32,"model_id":"qwen2.5-vl-72b","model_name":"Qwen2.5 VL 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.702,"normalized_score":0.702,"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":"2025-01-26","announcement_date":"2025-01-26","multimodal":true,"param_count":72000000000,"is_new":false},{"rank":33,"model_id":"qwen2.5-vl-32b","model_name":"Qwen2.5 VL 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.7,"normalized_score":0.7,"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":"2025-02-28","announcement_date":"2025-02-28","multimodal":true,"param_count":33500000000,"is_new":false},{"rank":34,"model_id":"kimi-k1.5","model_name":"Kimi-k1.5","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.7,"normalized_score":0.7,"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":true,"param_count":null,"is_new":false},{"rank":35,"model_id":"llama-4-scout","model_name":"Llama 4 Scout","organization_name":"Meta","organization_id":"meta","benchmark_score":0.694,"normalized_score":0.694,"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":36,"model_id":"claude-3-5-sonnet-20241022","model_name":"Claude 3.5 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.683,"normalized_score":0.683,"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":"2024-10-22","announcement_date":"2024-10-22","multimodal":true,"param_count":null,"is_new":false},{"rank":37,"model_id":"gemini-2.0-flash-lite","model_name":"Gemini 2.0 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.68,"normalized_score":0.68,"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":"2025-02-05","announcement_date":"2025-02-05","multimodal":true,"param_count":null,"is_new":false},{"rank":38,"model_id":"grok-2","model_name":"Grok-2","organization_name":"xAI","organization_id":"xai","benchmark_score":0.661,"normalized_score":0.661,"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":"2024-08-13","announcement_date":"2024-08-13","multimodal":true,"param_count":null,"is_new":false},{"rank":39,"model_id":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.659,"normalized_score":0.659,"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":"2024-05-01","announcement_date":"2024-05-01","multimodal":true,"param_count":null,"is_new":false},{"rank":40,"model_id":"pixtral-large","model_name":"Pixtral Large","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.64,"normalized_score":0.64,"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":"2024-11-18","announcement_date":"2024-11-18","multimodal":true,"param_count":124000000000,"is_new":false},{"rank":41,"model_id":"grok-2-mini","model_name":"Grok-2 mini","organization_name":"xAI","organization_id":"xai","benchmark_score":0.632,"normalized_score":0.632,"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":"2024-08-13","announcement_date":"2024-08-13","multimodal":true,"param_count":null,"is_new":false},{"rank":42,"model_id":"mistral-small-3.2-24b-instruct-2506","model_name":"Mistral Small 3.2 24B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.625,"normalized_score":0.625,"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":"2025-06-20","announcement_date":"2025-06-20","multimodal":true,"param_count":23600000000,"is_new":false},{"rank":43,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_name":"Google","organization_id":"google","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":"2024-05-01","announcement_date":"2024-05-01","multimodal":true,"param_count":null,"is_new":false},{"rank":44,"model_id":"nova-pro","model_name":"Nova Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.617,"normalized_score":0.617,"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":"2024-11-20","announcement_date":"2024-11-20","multimodal":true,"param_count":null,"is_new":false},{"rank":45,"model_id":"llama-3.2-90b-instruct","model_name":"Llama 3.2 90B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.603,"normalized_score":0.603,"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":"2024-09-25","announcement_date":"2024-09-25","multimodal":true,"param_count":90000000000,"is_new":false},{"rank":46,"model_id":"gpt-4o-mini-2024-07-18","model_name":"GPT-4o mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.594,"normalized_score":0.594,"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":"2024-07-18","announcement_date":"2024-07-18","multimodal":true,"param_count":null,"is_new":false},{"rank":47,"model_id":"mistral-small-3.1-24b-base-2503","model_name":"Mistral Small 3.1 24B Base","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.5927,"normalized_score":0.5927,"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":"2025-03-17","announcement_date":"2025-03-17","multimodal":true,"param_count":24000000000,"is_new":false},{"rank":48,"model_id":"mistral-small-3.1-24b-instruct-2503","model_name":"Mistral Small 3.1 24B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.5927,"normalized_score":0.5927,"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":"2025-03-17","announcement_date":"2025-03-17","multimodal":true,"param_count":24000000000,"is_new":false},{"rank":49,"model_id":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.592,"normalized_score":0.592,"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":"2025-03-27","announcement_date":"2025-03-27","multimodal":true,"param_count":7000000000,"is_new":false},{"rank":50,"model_id":"qwen2.5-vl-7b","model_name":"Qwen2.5 VL 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.586,"normalized_score":0.586,"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":"2025-01-26","announcement_date":"2025-01-26","multimodal":true,"param_count":8290000000,"is_new":false},{"rank":51,"model_id":"nova-lite","model_name":"Nova Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.562,"normalized_score":0.562,"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":"2024-11-20","announcement_date":"2024-11-20","multimodal":true,"param_count":null,"is_new":false},{"rank":52,"model_id":"gpt-4.1-nano-2025-04-14","model_name":"GPT-4.1 nano","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.554,"normalized_score":0.554,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":200.0,"context_window":1047576,"release_date":"2025-04-14","announcement_date":"2025-04-14","multimodal":true,"param_count":null,"is_new":false},{"rank":53,"model_id":"phi-4-multimodal-instruct","model_name":"Phi-4-multimodal-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.551,"normalized_score":0.551,"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":"2025-02-01","announcement_date":"2025-02-01","multimodal":true,"param_count":5600000000,"is_new":false},{"rank":54,"model_id":"gemini-1.5-flash-8b","model_name":"Gemini 1.5 Flash 8B","organization_name":"Google","organization_id":"google","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":"2024-03-15","announcement_date":"2024-03-15","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":55,"model_id":"grok-1.5v","model_name":"Grok-1.5V","organization_name":"xAI","organization_id":"xai","benchmark_score":0.536,"normalized_score":0.536,"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":"2024-04-12","announcement_date":"2024-04-12","multimodal":true,"param_count":null,"is_new":false},{"rank":56,"model_id":"grok-1.5","model_name":"Grok-1.5","organization_name":"xAI","organization_id":"xai","benchmark_score":0.536,"normalized_score":0.536,"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":"2024-03-28","announcement_date":"2024-03-28","multimodal":false,"param_count":null,"is_new":false},{"rank":57,"model_id":"pixtral-12b-2409","model_name":"Pixtral-12B","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.525,"normalized_score":0.525,"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":"2024-09-17","announcement_date":"2024-09-17","multimodal":true,"param_count":12400000000,"is_new":false},{"rank":58,"model_id":"deepseek-vl2","model_name":"DeepSeek VL2","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.511,"normalized_score":0.511,"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":"2024-12-13","announcement_date":"2024-12-13","multimodal":true,"param_count":27000000000,"is_new":false},{"rank":59,"model_id":"llama-3.2-11b-instruct","model_name":"Llama 3.2 11B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.507,"normalized_score":0.507,"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":"2024-09-25","announcement_date":"2024-09-25","multimodal":true,"param_count":10600000000,"is_new":false},{"rank":60,"model_id":"deepseek-vl2-small","model_name":"DeepSeek VL2 Small","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.48,"normalized_score":0.48,"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":"2024-12-13","announcement_date":"2024-12-13","multimodal":true,"param_count":16000000000,"is_new":false},{"rank":61,"model_id":"gemini-1.0-pro","model_name":"Gemini 1.0 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.479,"normalized_score":0.479,"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":"2024-02-15","announcement_date":"2024-02-15","multimodal":false,"param_count":null,"is_new":false},{"rank":62,"model_id":"phi-3.5-vision-instruct","model_name":"Phi-3.5-vision-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.43,"normalized_score":0.43,"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":"2024-08-23","announcement_date":"2024-08-23","multimodal":true,"param_count":4200000000,"is_new":false},{"rank":63,"model_id":"deepseek-vl2-tiny","model_name":"DeepSeek VL2 Tiny","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.407,"normalized_score":0.407,"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":"2024-12-13","announcement_date":"2024-12-13","multimodal":true,"param_count":3000000000,"is_new":false},{"rank":64,"model_id":"gpt-3.5-turbo-0125","model_name":"GPT-3.5 Turbo","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.0,"normalized_score":0.0,"verified":false,"self_reported":false,"provider_id":"openai","input_cost_per_million":0.5,"output_cost_per_million":1.5,"speed_rps":100.0,"context_window":16385,"release_date":"2023-03-21","announcement_date":"2023-03-21","multimodal":false,"param_count":null,"is_new":false}]}