{"total":11,"page":1,"per_page":20,"results":[{"id":"gpt-4o","name":"GPT-4o","creator":"OpenAI","params":"~1.8T (MoE)","context_length":128000,"license":"proprietary","training_data":["WebText2","Common Crawl","Books","Code","RLHF"],"benchmarks":{"MMLU":88.7,"HumanEval":90.2,"MATH":76.6,"MT-Bench":9.1,"BBH":84.1}},{"id":"o3","name":"o3","creator":"OpenAI","params":"unknown","context_length":200000,"license":"proprietary","training_data":["Common Crawl","Books","Code","RLHF","Reasoning traces"],"benchmarks":{"MMLU":91.4,"HumanEval":97.9,"MATH":96.7,"MT-Bench":9.6,"BBH":88.4}},{"id":"claude-3-5-sonnet","name":"Claude 3.5 Sonnet","creator":"Anthropic","params":"unknown","context_length":200000,"license":"proprietary","training_data":["Web data","Books","Code","Constitutional AI feedback"],"benchmarks":{"MMLU":88.3,"HumanEval":92,"MATH":71.1,"MT-Bench":9.4,"BBH":87.5}},{"id":"gemini-1-5-ultra","name":"Gemini 1.5 Ultra","creator":"Google DeepMind","params":"unknown","context_length":1000000,"license":"proprietary","training_data":["Web data","Books","Code","YouTube transcripts"],"benchmarks":{"MMLU":90,"HumanEval":84.1,"MATH":58.5,"MT-Bench":9.1,"BBH":83.2}},{"id":"apple-afm-server","name":"Apple AFM (Server)","creator":"Apple","params":"unknown","context_length":null,"license":"proprietary","training_data":["Licensed data","Synthetic data","Applebot web crawl"],"benchmarks":null},{"id":"apple-afm-ondevice","name":"Apple AFM (On-Device)","creator":"Apple","params":"~3B","context_length":4096,"license":"proprietary","training_data":["Licensed data","Synthetic data","Applebot web crawl"],"benchmarks":{"MMLU":60.9}},{"id":"llama-3-405b","name":"Llama 3 405B","creator":"Meta","params":"405B","context_length":128000,"license":"llama-3","training_data":["Common Crawl","GitHub","Wikipedia","Books","arXiv"],"benchmarks":{"MMLU":87.3,"HumanEval":89,"MATH":73.8,"MT-Bench":8.9,"BBH":81.3}},{"id":"deepseek-r1","name":"DeepSeek-R1","creator":"DeepSeek","params":"671B (MoE)","context_length":128000,"license":"mit","training_data":["Web data","Math","Code","Reasoning traces"],"benchmarks":{"MMLU":90.8,"HumanEval":92.3,"MATH":97.3,"MT-Bench":9,"BBH":86.7}},{"id":"deepseek-v3","name":"DeepSeek-V3","creator":"DeepSeek","params":"671B (MoE)","context_length":128000,"license":"mit","training_data":["Web (14.8T tokens)","Math","Code"],"benchmarks":{"MMLU":88.5,"HumanEval":89.9,"MATH":90.2,"MT-Bench":8.9,"BBH":85}},{"id":"mistral-large-2","name":"Mistral Large 2","creator":"Mistral AI","params":"123B","context_length":128000,"license":"mistral-research","training_data":["Web data","Code","Books"],"benchmarks":{"MMLU":84,"HumanEval":92.1,"MATH":69.9,"MT-Bench":8.6,"BBH":80.1}},{"id":"qwen-2-5-72b","name":"Qwen2.5 72B Instruct","creator":"Alibaba","params":"72B","context_length":128000,"license":"qwen","training_data":["Web data","Math","Code","Multilingual corpora"],"benchmarks":{"MMLU":86.1,"HumanEval":86.2,"MATH":83.1,"MT-Bench":8.8,"BBH":79.4}}]}