{"benchmark_id":"aime-2025","benchmark_name":"AIME 2025","benchmark_description":"All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":116,"entries":[{"rank":1,"model_id":"gpt-5.2-2025-12-11","model_name":"GPT-5.2","organization_name":"OpenAI","organization_id":"openai","benchmark_score":1.0,"normalized_score":1.0,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":1.75,"output_cost_per_million":14.0,"speed_rps":100.0,"context_window":400000,"release_date":"2025-12-11","announcement_date":"2025-12-11","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gpt-5.2-pro-2025-12-11","model_name":"GPT-5.2 Pro","organization_name":"OpenAI","organization_id":"openai","benchmark_score":1.0,"normalized_score":1.0,"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":"2025-12-11","announcement_date":"2025-12-11","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"gemini-3-pro-preview","model_name":"Gemini 3 Pro","organization_name":"Google","organization_id":"google","benchmark_score":1.0,"normalized_score":1.0,"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":"2025-11-18","announcement_date":"2025-11-18","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":1.0,"normalized_score":1.0,"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":5,"model_id":"grok-4-heavy","model_name":"Grok-4 Heavy","organization_name":"xAI","organization_id":"xai","benchmark_score":1.0,"normalized_score":1.0,"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":6,"model_id":"claude-opus-4-6","model_name":"Claude Opus 4.6","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.9979,"normalized_score":0.9979,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":5.0,"output_cost_per_million":25.0,"speed_rps":42.0,"context_window":1000000,"release_date":"2026-02-05","announcement_date":"2026-02-05","multimodal":true,"param_count":null,"is_new":false},{"rank":7,"model_id":"gemini-3-flash-preview","model_name":"Gemini 3 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.997,"normalized_score":0.997,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":0.5,"output_cost_per_million":3.0,"speed_rps":null,"context_window":1000000,"release_date":"2025-12-17","announcement_date":"2025-12-17","multimodal":true,"param_count":null,"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":0.996,"normalized_score":0.996,"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":"gpt-5.1-high-2025-11-12","model_name":"GPT-5.1 High","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.996,"normalized_score":0.996,"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":10,"model_id":"nemotron-3-nano-30b-a3b","model_name":"Nemotron 3 Nano (30B A3B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.992,"normalized_score":0.992,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.06,"output_cost_per_million":0.24,"speed_rps":null,"context_window":262144,"release_date":"2025-12-15","announcement_date":"2025-12-15","multimodal":false,"param_count":32000000000,"is_new":false},{"rank":11,"model_id":"gpt-oss-20b-high","model_name":"GPT OSS 20B High","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.987,"normalized_score":0.987,"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":"2025-08-05","announcement_date":"2025-08-05","multimodal":false,"param_count":20900000000,"is_new":false},{"rank":12,"model_id":"gpt-5.1-medium-2025-11-12","model_name":"GPT-5.1 Medium","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.984,"normalized_score":0.984,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":1.25,"output_cost_per_million":10.0,"speed_rps":90.0,"context_window":400000,"release_date":"2025-11-12","announcement_date":"2025-11-12","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"seed-2.0-pro","model_name":"Seed 2.0 Pro","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.983,"normalized_score":0.983,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.5,"output_cost_per_million":3.0,"speed_rps":null,"context_window":256000,"release_date":"2026-02-14","announcement_date":"2026-02-14","multimodal":true,"param_count":null,"is_new":false},{"rank":14,"model_id":"step-3.5-flash","model_name":"Step-3.5-Flash","organization_name":"StepFun","organization_id":"stepfun","benchmark_score":0.973,"normalized_score":0.973,"verified":false,"self_reported":true,"provider_id":"stepfun","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":150.0,"context_window":65536,"release_date":"2026-02-02","announcement_date":"2026-02-02","multimodal":false,"param_count":196000000000,"is_new":false},{"rank":15,"model_id":"mai-thinking-1","model_name":"MAI-Thinking-1","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.97,"normalized_score":0.97,"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":"2026-06-02","announcement_date":"2026-06-02","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":16,"model_id":"sarvam-105b","model_name":"Sarvam-105B","organization_name":"Sarvam AI","organization_id":"sarvamai","benchmark_score":0.967,"normalized_score":0.967,"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":105000000000,"is_new":false},{"rank":17,"model_id":"sarvam-30b","model_name":"Sarvam-30B","organization_name":"Sarvam AI","organization_id":"sarvamai","benchmark_score":0.967,"normalized_score":0.967,"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":18,"model_id":"gpt-5.1-codex-high","model_name":"GPT-5.1 Codex High","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.967,"normalized_score":0.967,"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":19,"model_id":"kimi-k2.5","model_name":"Kimi K2.5","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.961,"normalized_score":0.961,"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":"2026-01-27","announcement_date":"2026-01-27","multimodal":true,"param_count":1000000000000,"is_new":false},{"rank":20,"model_id":"deepseek-v3.2-speciale","model_name":"DeepSeek-V3.2-Speciale","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.96,"normalized_score":0.96,"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":21,"model_id":"glm-4.7","model_name":"GLM-4.7","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.957,"normalized_score":0.957,"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":"2025-12-22","announcement_date":"2025-12-22","multimodal":true,"param_count":358000000000,"is_new":false},{"rank":22,"model_id":"gpt-5-high-2025-08-07","model_name":"GPT-5 High","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.946,"normalized_score":0.946,"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":23,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.946,"normalized_score":0.946,"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":24,"model_id":"mimo-v2-flash","model_name":"MiMo-V2-Flash","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.941,"normalized_score":0.941,"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":"2025-12-16","announcement_date":"2025-12-16","multimodal":false,"param_count":309000000000,"is_new":false},{"rank":25,"model_id":"gpt-5.1-2025-11-13","model_name":"GPT-5.1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.94,"normalized_score":0.94,"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":26,"model_id":"gpt-5.1-instant-2025-11-12","model_name":"GPT-5.1 Instant","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.94,"normalized_score":0.94,"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":27,"model_id":"gpt-5.1-thinking-2025-11-12","model_name":"GPT-5.1 Thinking","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.94,"normalized_score":0.94,"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":28,"model_id":"glm-4.6","model_name":"GLM-4.6","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.939,"normalized_score":0.939,"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":"2025-09-30","announcement_date":"2025-09-30","multimodal":true,"param_count":357000000000,"is_new":false},{"rank":29,"model_id":"grok-3","model_name":"Grok-3","organization_name":"xAI","organization_id":"xai","benchmark_score":0.933,"normalized_score":0.933,"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":30,"model_id":"deepseek-reasoner","model_name":"DeepSeek-V3.2 (Thinking)","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.931,"normalized_score":0.931,"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":31,"model_id":"deepseek-v3.2","model_name":"DeepSeek-V3.2","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.931,"normalized_score":0.931,"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":32,"model_id":"seed-2.0-lite","model_name":"Seed 2.0 Lite","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.93,"normalized_score":0.93,"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":"2026-02-14","announcement_date":"2026-02-14","multimodal":true,"param_count":null,"is_new":false},{"rank":33,"model_id":"exaone-4.5-33b","model_name":"EXAONE 4.5 33B","organization_name":"LG AI Research","organization_id":"lg","benchmark_score":0.929,"normalized_score":0.929,"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":34,"model_id":"k-exaone-236b-a23b","model_name":"K-EXAONE-236B-A23B","organization_name":"LG AI Research","organization_id":"lg","benchmark_score":0.928,"normalized_score":0.928,"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":"2025-12-31","announcement_date":"2025-12-31","multimodal":false,"param_count":236000000000,"is_new":false},{"rank":35,"model_id":"o4-mini","model_name":"o4-mini","organization_name":"OpenAI","organization_id":"openai","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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":null,"is_new":false},{"rank":36,"model_id":"gpt-oss-120b-high","model_name":"GPT OSS 120B High","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.925,"normalized_score":0.925,"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":"2025-08-05","announcement_date":"2025-08-05","multimodal":false,"param_count":116800000000,"is_new":false},{"rank":37,"model_id":"nova-2-pro","model_name":"Nova 2 Pro","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.923,"normalized_score":0.923,"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":38,"model_id":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3-235B-A22B-Thinking-2507","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.923,"normalized_score":0.923,"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":"2025-07-25","announcement_date":"2025-07-25","multimodal":false,"param_count":235000000000,"is_new":false},{"rank":39,"model_id":"nova-2-omni","model_name":"Nova 2 Omni","organization_name":"Amazon","organization_id":"amazon","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":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false},{"rank":40,"model_id":"grok-4-fast","model_name":"Grok 4 Fast","organization_name":"xAI","organization_id":"xai","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":"2025-08-28","announcement_date":"2025-08-28","multimodal":true,"param_count":null,"is_new":false},{"rank":41,"model_id":"grok-4","model_name":"Grok-4","organization_name":"xAI","organization_id":"xai","benchmark_score":0.917,"normalized_score":0.917,"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":42,"model_id":"glm-4.7-flash","model_name":"GLM-4.7-Flash","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.916,"normalized_score":0.916,"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":"2026-01-19","announcement_date":"2026-01-19","multimodal":false,"param_count":30000000000,"is_new":false},{"rank":43,"model_id":"mercury-2","model_name":"Mercury 2","organization_name":"Inception","organization_id":"inceptionlabs","benchmark_score":0.911,"normalized_score":0.911,"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":44,"model_id":"gpt-5-mini-2025-08-07","model_name":"GPT-5 mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.911,"normalized_score":0.911,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":0.25,"output_cost_per_million":2.0,"speed_rps":200.0,"context_window":400000,"release_date":"2025-08-07","announcement_date":"2025-08-07","multimodal":true,"param_count":null,"is_new":false},{"rank":45,"model_id":"nova-2-lite","model_name":"Nova 2 Lite","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.91,"normalized_score":0.91,"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":46,"model_id":"grok-3-mini","model_name":"Grok-3 Mini","organization_name":"xAI","organization_id":"xai","benchmark_score":0.908,"normalized_score":0.908,"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":47,"model_id":"longcat-flash-thinking","model_name":"LongCat-Flash-Thinking","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.906,"normalized_score":0.906,"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":48,"model_id":"nemotron-3-super-120b-a12b","model_name":"Nemotron 3 Super (120B A12B)","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.9021,"normalized_score":0.9021,"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":49,"model_id":"command-a-plus-05-2026","model_name":"Command A+","organization_name":"Cohere","organization_id":"cohere","benchmark_score":0.9,"normalized_score":0.9,"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":50,"model_id":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.897,"normalized_score":0.897,"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":true,"param_count":236000000000,"is_new":false},{"rank":51,"model_id":"deepseek-v3.2-exp","model_name":"DeepSeek-V3.2-Exp","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.893,"normalized_score":0.893,"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":52,"model_id":"gpt-5-medium-2025-08-07","model_name":"GPT-5 Medium","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.889,"normalized_score":0.889,"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":53,"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":0.88,"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":"2025-06-05","announcement_date":"2025-06-05","multimodal":true,"param_count":null,"is_new":false},{"rank":54,"model_id":"qwen3-next-80b-a3b-thinking","model_name":"Qwen3-Next-80B-A3B-Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","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":"2025-09-10","announcement_date":"2025-09-10","multimodal":false,"param_count":80000000000,"is_new":false},{"rank":55,"model_id":"step3-vl-10b","model_name":"Step3-VL-10B","organization_name":"StepFun","organization_id":"stepfun","benchmark_score":0.877,"normalized_score":0.877,"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":56,"model_id":"deepseek-r1-0528","model_name":"DeepSeek-R1-0528","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.875,"normalized_score":0.875,"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":57,"model_id":"ernie-5.0","model_name":"ERNIE 5.0","organization_name":"Baidu","organization_id":"baidu","benchmark_score":0.87,"normalized_score":0.87,"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":"2026-01-22","announcement_date":"2026-01-22","multimodal":true,"param_count":null,"is_new":false},{"rank":58,"model_id":"claude-sonnet-4-5-20250929","model_name":"Claude Sonnet 4.5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.87,"normalized_score":0.87,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":42.0,"context_window":200000,"release_date":"2025-09-29","announcement_date":"2025-09-29","multimodal":true,"param_count":null,"is_new":false},{"rank":59,"model_id":"o3-2025-04-16","model_name":"o3","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.864,"normalized_score":0.864,"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":60,"model_id":"mistral-medium-3-5","model_name":"Mistral Medium 3.5","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.863,"normalized_score":0.863,"verified":false,"self_reported":true,"provider_id":"mistral","input_cost_per_million":1.5,"output_cost_per_million":7.5,"speed_rps":null,"context_window":256000,"release_date":"2026-04-29","announcement_date":"2026-04-29","multimodal":true,"param_count":128000000000,"is_new":false},{"rank":61,"model_id":"gpt-5-nano-2025-08-07","model_name":"GPT-5 nano","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.852,"normalized_score":0.852,"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":62,"model_id":"ministral-14b-latest","model_name":"Ministral 3 (14B Reasoning 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.85,"normalized_score":0.85,"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":63,"model_id":"mistral-small-latest","model_name":"Mistral Small 4","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.838,"normalized_score":0.838,"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":64,"model_id":"qwen3-vl-32b-thinking","model_name":"Qwen3 VL 32B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.837,"normalized_score":0.837,"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":true,"param_count":33000000000,"is_new":false},{"rank":65,"model_id":"qwen3-vl-30b-a3b-thinking","model_name":"Qwen3 VL 30B A3B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.831,"normalized_score":0.831,"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":true,"param_count":31000000000,"is_new":false},{"rank":66,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.83,"normalized_score":0.83,"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":67,"model_id":"qwen3-max","model_name":"Qwen3 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","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":"2025-12-15","announcement_date":"2025-12-15","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":68,"model_id":"qwen3-235b-a22b","model_name":"Qwen3 235B A22B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.815,"normalized_score":0.815,"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":69,"model_id":"gpt-5.5-instant","model_name":"GPT-5.5 Instant","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.812,"normalized_score":0.812,"verified":false,"self_reported":true,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"speed_rps":100.0,"context_window":400000,"release_date":"2026-05-05","announcement_date":"2026-05-05","multimodal":true,"param_count":null,"is_new":false},{"rank":70,"model_id":"minimax-m2.1","model_name":"MiniMax M2.1","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.81,"normalized_score":0.81,"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":71,"model_id":"claude-haiku-4-5-20251001","model_name":"Claude Haiku 4.5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.807,"normalized_score":0.807,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":1.0,"output_cost_per_million":5.0,"speed_rps":100.0,"context_window":200000,"release_date":"2025-10-15","announcement_date":"2025-10-15","multimodal":true,"param_count":null,"is_new":false},{"rank":72,"model_id":"qwen3-vl-8b-thinking","model_name":"Qwen3 VL 8B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.803,"normalized_score":0.803,"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":true,"param_count":9000000000,"is_new":false},{"rank":73,"model_id":"ministral-8b-latest","model_name":"Ministral 3 (8B Reasoning 2512)","organization_name":"Mistral AI","organization_id":"mistral","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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":74,"model_id":"minicpm-sala","model_name":"MiniCPM-SALA","organization_name":"OpenBMB","organization_id":"openbmb","benchmark_score":0.7833,"normalized_score":0.7833,"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":75,"model_id":"minimax-m2","model_name":"MiniMax M2","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.78,"normalized_score":0.78,"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":76,"model_id":"claude-opus-4-1-20250805","model_name":"Claude Opus 4.1","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.78,"normalized_score":0.78,"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":"2025-08-05","announcement_date":"2025-08-05","multimodal":true,"param_count":null,"is_new":false},{"rank":77,"model_id":"phi-4-reasoning-plus","model_name":"Phi 4 Reasoning Plus","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.78,"normalized_score":0.78,"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":78,"model_id":"minimax-m1-80k","model_name":"MiniMax M1 80K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.769,"normalized_score":0.769,"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":79,"model_id":"claude-opus-4-20250514","model_name":"Claude Opus 4","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.755,"normalized_score":0.755,"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":80,"model_id":"qwen3-vl-235b-a22b-instruct","model_name":"Qwen3 VL 235B A22B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.747,"normalized_score":0.747,"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":true,"param_count":236000000000,"is_new":false},{"rank":81,"model_id":"minimax-m1-40k","model_name":"MiniMax M1 40K","organization_name":"MiniMax","organization_id":"minimax","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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false},{"rank":82,"model_id":"qwen3-vl-4b-thinking","model_name":"Qwen3 VL 4B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.745,"normalized_score":0.745,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":1.0,"speed_rps":null,"context_window":262144,"release_date":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":4000000000,"is_new":false},{"rank":83,"model_id":"qwen3-32b","model_name":"Qwen3 32B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.729,"normalized_score":0.729,"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":84,"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":0.725,"normalized_score":0.725,"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":85,"model_id":"ministral-3b-latest","model_name":"Min  istral 3 (3B Reasoning 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.721,"normalized_score":0.721,"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":86,"model_id":"nvidia-nemotron-nano-9b-v2","model_name":"Nemotron Nano 9B v2","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.721,"normalized_score":0.721,"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":87,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_name":"Google","organization_id":"google","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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":88,"model_id":"qwen3-30b-a3b","model_name":"Qwen3 30B A3B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.709,"normalized_score":0.709,"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":89,"model_id":"claude-sonnet-4-20250514","model_name":"Claude Sonnet 4","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.705,"normalized_score":0.705,"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":90,"model_id":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3-235B-A22B-Instruct-2507","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":"2025-07-22","announcement_date":"2025-07-22","multimodal":false,"param_count":235000000000,"is_new":false},{"rank":91,"model_id":"qwen3-next-80b-a3b-instruct","model_name":"Qwen3-Next-80B-A3B-Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.695,"normalized_score":0.695,"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":"2025-09-10","announcement_date":"2025-09-10","multimodal":false,"param_count":80000000000,"is_new":false},{"rank":92,"model_id":"qwen3-vl-30b-a3b-instruct","model_name":"Qwen3 VL 30B A3B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.693,"normalized_score":0.693,"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":true,"param_count":31000000000,"is_new":false},{"rank":93,"model_id":"qwen3-vl-32b-instruct","model_name":"Qwen3 VL 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.662,"normalized_score":0.662,"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":true,"param_count":33000000000,"is_new":false},{"rank":94,"model_id":"magistral-medium","model_name":"Magistral Medium","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.649,"normalized_score":0.649,"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":95,"model_id":"longcat-flash-lite","model_name":"LongCat-Flash-Lite","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.6323,"normalized_score":0.6323,"verified":false,"self_reported":true,"provider_id":"meituan","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":500.0,"context_window":256000,"release_date":"2026-02-05","announcement_date":"2026-02-05","multimodal":false,"param_count":68500000000,"is_new":false},{"rank":96,"model_id":"phi-4-reasoning","model_name":"Phi 4 Reasoning","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.629,"normalized_score":0.629,"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":97,"model_id":"magistral-small-2506","model_name":"Magistral Small 2506","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.6276,"normalized_score":0.6276,"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":98,"model_id":"longcat-flash-chat","model_name":"LongCat-Flash-Chat","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.6125,"normalized_score":0.6125,"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":99,"model_id":"llama-3.3-nemotron-super-49b-v1","model_name":"Llama-3.3 Nemotron Super 49B v1","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.584,"normalized_score":0.584,"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":"2025-03-18","announcement_date":"2025-03-18","multimodal":false,"param_count":49900000000,"is_new":false},{"rank":100,"model_id":"claude-3-7-sonnet-20250219","model_name":"Claude 3.7 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","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":"2025-02-24","announcement_date":"2025-02-24","multimodal":true,"param_count":null,"is_new":false},{"rank":101,"model_id":"lfm-2.5-2.6b","model_name":"LFM2.5-2.6B","organization_name":"Liquid AI","organization_id":"liquid","benchmark_score":0.5187,"normalized_score":0.5187,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-08-04","announcement_date":"2026-08-04","multimodal":false,"param_count":2690000000,"is_new":false},{"rank":102,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.498,"normalized_score":0.498,"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":103,"model_id":"deepseek-v3.1","model_name":"DeepSeek-V3.1","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.498,"normalized_score":0.498,"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":104,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.495,"normalized_score":0.495,"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":105,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.495,"normalized_score":0.495,"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":106,"model_id":"llama-3.1-nemotron-nano-8b-v1","model_name":"Llama 3.1 Nemotron Nano 8B V1","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.471,"normalized_score":0.471,"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":"2025-03-18","announcement_date":"2025-03-18","multimodal":false,"param_count":8000000000,"is_new":false},{"rank":107,"model_id":"qwen3-vl-4b-instruct","model_name":"Qwen3 VL 4B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.466,"normalized_score":0.466,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.6,"speed_rps":null,"context_window":262144,"release_date":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":4000000000,"is_new":false},{"rank":108,"model_id":"gpt-4.1-2025-04-14","model_name":"GPT-4.1","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.464,"normalized_score":0.464,"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":109,"model_id":"qwen3-vl-8b-instruct","model_name":"Qwen3 VL 8B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.459,"normalized_score":0.459,"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":true,"param_count":9000000000,"is_new":false},{"rank":110,"model_id":"gpt-5.1-codex-mini","model_name":"GPT-5.1 Codex Mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.421,"normalized_score":0.421,"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":111,"model_id":"gpt-4.1-mini-2025-04-14","model_name":"GPT-4.1 mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.402,"normalized_score":0.402,"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":112,"model_id":"gemini-diffusion","model_name":"Gemini Diffusion","organization_name":"Google","organization_id":"google","benchmark_score":0.233,"normalized_score":0.233,"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":113,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.116,"normalized_score":0.116,"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":114,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_name":"Google","organization_id":"google","benchmark_score":0.116,"normalized_score":0.116,"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":115,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_name":"Google","organization_id":"google","benchmark_score":0.067,"normalized_score":0.067,"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":116,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_name":"Google","organization_id":"google","benchmark_score":0.067,"normalized_score":0.067,"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}]}