{"benchmark_id":"humaneval","benchmark_name":"HumanEval","benchmark_description":"A benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics","max_score":1.0,"categories":["reasoning","code"],"modality":"text","total_models":66,"entries":[{"rank":1,"model_id":"minicpm-sala","model_name":"MiniCPM-SALA","organization_name":"OpenBMB","organization_id":"openbmb","benchmark_score":0.9512,"normalized_score":0.9512,"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":"2026-02-11","announcement_date":"2026-02-11","multimodal":false,"param_count":9477203968,"is_new":false},{"rank":2,"model_id":"kimi-k2-0905","model_name":"Kimi K2 0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.945,"normalized_score":0.945,"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":3,"model_id":"claude-3-5-sonnet-20241022","model_name":"Claude 3.5 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.937,"normalized_score":0.937,"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":4,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.934,"normalized_score":0.934,"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":5,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.933,"normalized_score":0.933,"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":"2025-07-11","announcement_date":"2025-07-11","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":6,"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":0.927,"normalized_score":0.927,"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":7,"model_id":"o1-mini","model_name":"o1-mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.924,"normalized_score":0.924,"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":"2024-09-12","announcement_date":"2024-09-12","multimodal":false,"param_count":null,"is_new":false},{"rank":8,"model_id":"sarvam-30b","model_name":"Sarvam-30B","organization_name":"Sarvam AI","organization_id":"sarvamai","benchmark_score":0.921,"normalized_score":0.921,"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":"2026-03-06","announcement_date":"2026-03-06","multimodal":false,"param_count":30000000000,"is_new":false},{"rank":9,"model_id":"mistral-large-2-2407","model_name":"Mistral Large 2","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.92,"normalized_score":0.92,"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":"2024-07-24","announcement_date":"2024-07-24","multimodal":false,"param_count":123000000000,"is_new":false},{"rank":10,"model_id":"claude-3-5-sonnet-20240620","model_name":"Claude 3.5 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.92,"normalized_score":0.92,"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":"2024-06-21","announcement_date":"2024-06-21","multimodal":true,"param_count":null,"is_new":false},{"rank":11,"model_id":"qwen2.5-vl-32b","model_name":"Qwen2.5 VL 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.915,"normalized_score":0.915,"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":12,"model_id":"gpt-4o-2024-05-13","model_name":"GPT-4o","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.902,"normalized_score":0.902,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":2.5,"output_cost_per_million":10.0,"speed_rps":100.0,"context_window":128000,"release_date":"2024-05-13","announcement_date":"2024-05-13","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"granite-3.3-8b-instruct","model_name":"Granite 3.3 8B Instruct","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.8973,"normalized_score":0.8973,"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":8000000000,"is_new":false},{"rank":14,"model_id":"granite-3.3-8b-base","model_name":"Granite 3.3 8B Base","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.8973,"normalized_score":0.8973,"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":8170000000,"is_new":false},{"rank":15,"model_id":"gemini-diffusion","model_name":"Gemini Diffusion","organization_name":"Google","organization_id":"google","benchmark_score":0.896,"normalized_score":0.896,"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":16,"model_id":"nova-pro","model_name":"Nova Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.89,"normalized_score":0.89,"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":17,"model_id":"llama-3.1-405b-instruct","model_name":"Llama 3.1 405B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.89,"normalized_score":0.89,"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":405000000000,"is_new":false},{"rank":18,"model_id":"deepseek-v2.5","model_name":"DeepSeek-V2.5","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.89,"normalized_score":0.89,"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":"2024-05-08","announcement_date":"2024-05-08","multimodal":false,"param_count":236000000000,"is_new":false},{"rank":19,"model_id":"longcat-flash-chat","model_name":"LongCat-Flash-Chat","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.8841,"normalized_score":0.8841,"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":20,"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":0.8841,"normalized_score":0.8841,"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":21,"model_id":"llama-3.3-70b-instruct","model_name":"Llama 3.3 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.884,"normalized_score":0.884,"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":"2024-12-06","announcement_date":"2024-12-06","multimodal":false,"param_count":70000000000,"is_new":false},{"rank":22,"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":0.884,"normalized_score":0.884,"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":23,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.884,"normalized_score":0.884,"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":32500000000,"is_new":false},{"rank":24,"model_id":"grok-2","model_name":"Grok-2","organization_name":"xAI","organization_id":"xai","benchmark_score":0.884,"normalized_score":0.884,"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":25,"model_id":"o1-2024-12-17","model_name":"o1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.881,"normalized_score":0.881,"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":26,"model_id":"claude-3-5-haiku-20241022","model_name":"Claude 3.5 Haiku","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.881,"normalized_score":0.881,"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":false,"param_count":null,"is_new":false},{"rank":27,"model_id":"gpt-4.5","model_name":"GPT-4.5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.88,"normalized_score":0.88,"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":28,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_name":"Google","organization_id":"google","benchmark_score":0.878,"normalized_score":0.878,"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":29,"model_id":"gpt-4o-mini-2024-07-18","model_name":"GPT-4o mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.872,"normalized_score":0.872,"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":30,"model_id":"gpt-4-turbo-2024-04-09","model_name":"GPT-4 Turbo","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.871,"normalized_score":0.871,"verified":false,"self_reported":true,"provider_id":"azure","input_cost_per_million":10.0,"output_cost_per_million":30.0,"speed_rps":97.0,"context_window":128000,"release_date":"2024-04-09","announcement_date":"2024-04-09","multimodal":false,"param_count":null,"is_new":false},{"rank":31,"model_id":"qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.866,"normalized_score":0.866,"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":32,"model_id":"qwen2-72b-instruct","model_name":"Qwen2 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.86,"normalized_score":0.86,"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":72000000000,"is_new":false},{"rank":33,"model_id":"grok-2-mini","model_name":"Grok-2 mini","organization_name":"xAI","organization_id":"xai","benchmark_score":0.857,"normalized_score":0.857,"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":34,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_name":"Google","organization_id":"google","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":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":12000000000,"is_new":false},{"rank":35,"model_id":"nova-lite","model_name":"Nova Lite","organization_name":"Amazon","organization_id":"amazon","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":"2024-11-20","announcement_date":"2024-11-20","multimodal":true,"param_count":null,"is_new":false},{"rank":36,"model_id":"claude-3-opus-20240229","model_name":"Claude 3 Opus","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.849,"normalized_score":0.849,"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":"2024-02-29","announcement_date":"2024-02-29","multimodal":true,"param_count":null,"is_new":false},{"rank":37,"model_id":"mistral-small-24b-instruct-2501","model_name":"Mistral Small 3 24B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.848,"normalized_score":0.848,"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":"2025-01-30","announcement_date":"2025-01-30","multimodal":false,"param_count":24000000000,"is_new":false},{"rank":38,"model_id":"qwen-2.5-7b-instruct","model_name":"Qwen2.5 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.848,"normalized_score":0.848,"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":39,"model_id":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.841,"normalized_score":0.841,"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":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.835,"normalized_score":0.835,"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":14700000000,"is_new":false},{"rank":41,"model_id":"phi-4","model_name":"Phi 4","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.826,"normalized_score":0.826,"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":"2024-12-12","announcement_date":"2024-12-12","multimodal":false,"param_count":14700000000,"is_new":false},{"rank":42,"model_id":"granite-4.0-tiny-preview","model_name":"IBM Granite 4.0 Tiny Preview","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.824,"normalized_score":0.824,"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":"2025-05-02","announcement_date":"2025-05-02","multimodal":false,"param_count":7000000000,"is_new":false},{"rank":43,"model_id":"nova-micro","model_name":"Nova Micro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.811,"normalized_score":0.811,"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":false,"param_count":null,"is_new":false},{"rank":44,"model_id":"codestral-22b","model_name":"Codestral-22B","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.811,"normalized_score":0.811,"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":"2024-05-29","announcement_date":"2024-05-29","multimodal":false,"param_count":22200000000,"is_new":false},{"rank":45,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.805,"normalized_score":0.805,"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":70000000000,"is_new":false},{"rank":46,"model_id":"qwen2-7b-instruct","model_name":"Qwen2 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.799,"normalized_score":0.799,"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":47,"model_id":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","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":"2025-03-27","announcement_date":"2025-03-27","multimodal":true,"param_count":7000000000,"is_new":false},{"rank":48,"model_id":"claude-3-haiku-20240307","model_name":"Claude 3 Haiku","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.759,"normalized_score":0.759,"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":"2024-03-13","announcement_date":"2024-03-13","multimodal":true,"param_count":null,"is_new":false},{"rank":49,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_name":"Google","organization_id":"google","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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":50,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_name":"Google","organization_id":"google","benchmark_score":0.75,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false},{"rank":51,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.743,"normalized_score":0.743,"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":52,"model_id":"grok-1.5","model_name":"Grok-1.5","organization_name":"xAI","organization_id":"xai","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":"2024-03-28","announcement_date":"2024-03-28","multimodal":false,"param_count":null,"is_new":false},{"rank":53,"model_id":"claude-3-sonnet-20240229","model_name":"Claude 3 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.73,"normalized_score":0.73,"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":"2024-02-29","announcement_date":"2024-02-29","multimodal":true,"param_count":null,"is_new":false},{"rank":54,"model_id":"llama-3.1-8b-instruct","model_name":"Llama 3.1 8B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.726,"normalized_score":0.726,"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":8000000000,"is_new":false},{"rank":55,"model_id":"pixtral-12b-2409","model_name":"Pixtral-12B","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.72,"normalized_score":0.72,"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":56,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_name":"Google","organization_id":"google","benchmark_score":0.713,"normalized_score":0.713,"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":57,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_name":"Microsoft","organization_id":"microsoft","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":"2024-08-23","announcement_date":"2024-08-23","multimodal":false,"param_count":60000000000,"is_new":false},{"rank":58,"model_id":"gpt-3.5-turbo-0125","model_name":"GPT-3.5 Turbo","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.68,"normalized_score":0.68,"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},{"rank":59,"model_id":"gpt-4-0613","model_name":"GPT-4","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.67,"normalized_score":0.67,"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":"2023-06-13","announcement_date":"2023-06-13","multimodal":true,"param_count":null,"is_new":false},{"rank":60,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.665,"normalized_score":0.665,"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":61,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_name":"Google","organization_id":"google","benchmark_score":0.665,"normalized_score":0.665,"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":62,"model_id":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.628,"normalized_score":0.628,"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":false,"param_count":3800000000,"is_new":false},{"rank":63,"model_id":"gemma-2-27b-it","model_name":"Gemma 2 27B","organization_name":"Google","organization_id":"google","benchmark_score":0.518,"normalized_score":0.518,"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":"2024-06-27","announcement_date":"2024-06-27","multimodal":false,"param_count":27200000000,"is_new":false},{"rank":64,"model_id":"gemma-3-1b-it","model_name":"Gemma 3 1B","organization_name":"Google","organization_id":"google","benchmark_score":0.415,"normalized_score":0.415,"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},{"rank":65,"model_id":"gemma-2-9b-it","model_name":"Gemma 2 9B","organization_name":"Google","organization_id":"google","benchmark_score":0.402,"normalized_score":0.402,"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":"2024-06-27","announcement_date":"2024-06-27","multimodal":false,"param_count":9240000000,"is_new":false},{"rank":66,"model_id":"ministral-8b-instruct-2410","model_name":"Ministral 8B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.348,"normalized_score":0.348,"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":"2024-10-16","announcement_date":"2024-10-16","multimodal":false,"param_count":8019808256,"is_new":false}]}