{"runAt":"2026-08-08T14:32:00Z","runs":5,"region":"us-east-1","source":"https://allaiask.com/benchmarks","license":"https://allaiask.com/terms","results":[{"modelId":"cerebras-gpt-oss-120b","name":"GPT-OSS 120B (Cerebras)","provider":"Cerebras","rank":1,"ttftMs":90,"tokensPerSecond":2450,"p95TokensPerSecond":2082.5,"samples":5,"estimated":false,"costPerMTokPerSec":0.0002},{"modelId":"cerebras-glm-4.7","name":"GLM 4.7 (Cerebras)","provider":"Cerebras","rank":2,"ttftMs":110,"tokensPerSecond":1980,"p95TokensPerSecond":1702.8,"samples":5,"estimated":false,"costPerMTokPerSec":0.0012},{"modelId":"gpt-oss-20b","name":"GPT-OSS 20B","provider":"Groq","rank":3,"ttftMs":140,"tokensPerSecond":1120,"p95TokensPerSecond":974.4,"samples":5,"estimated":false,"costPerMTokPerSec":0.0001},{"modelId":"gpt-oss-120b","name":"GPT-OSS 120B","provider":"Groq","rank":4,"ttftMs":160,"tokensPerSecond":780,"p95TokensPerSecond":639.6,"samples":5,"estimated":false,"costPerMTokPerSec":0.0003},{"modelId":"qwen3.8-30b","name":"Qwen 3.8 30B","provider":"Groq","rank":5,"ttftMs":150,"tokensPerSecond":690,"p95TokensPerSecond":634.8,"samples":5,"estimated":false,"costPerMTokPerSec":0.0017},{"modelId":"nova-micro","name":"Amazon Nova Micro","provider":"Amazon","rank":6,"ttftMs":220,"tokensPerSecond":168,"p95TokensPerSecond":142.8,"samples":5,"estimated":false,"costPerMTokPerSec":0.0004},{"modelId":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","provider":"Google","rank":7,"ttftMs":240,"tokensPerSecond":162,"p95TokensPerSecond":129.6,"samples":5,"estimated":false,"costPerMTokPerSec":0.0035},{"modelId":"ministral-8b","name":"Ministral 8B","provider":"Mistral","rank":8,"ttftMs":210,"tokensPerSecond":158,"p95TokensPerSecond":131.14,"samples":5,"estimated":false,"costPerMTokPerSec":0.0009},{"modelId":"claude-haiku-4-5","name":"Claude Haiku 4.5","provider":"Anthropic","rank":9,"ttftMs":260,"tokensPerSecond":148,"p95TokensPerSecond":118.4,"samples":5,"estimated":false,"costPerMTokPerSec":0.0135},{"modelId":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"DeepSeek","rank":10,"ttftMs":280,"tokensPerSecond":132,"p95TokensPerSecond":118.8,"samples":5,"estimated":false,"costPerMTokPerSec":0.0013},{"modelId":"gpt-5.6-luna","name":"GPT-5.6 Luna","provider":"OpenAI","rank":11,"ttftMs":300,"tokensPerSecond":126,"p95TokensPerSecond":108.36,"samples":5,"estimated":false,"costPerMTokPerSec":0.0036},{"modelId":"mistral-small","name":"Mistral Small 3.1","provider":"Mistral","rank":12,"ttftMs":260,"tokensPerSecond":121,"p95TokensPerSecond":110.11,"samples":5,"estimated":false,"costPerMTokPerSec":0.0022},{"modelId":"codestral","name":"Codestral","provider":"Mistral","rank":13,"ttftMs":270,"tokensPerSecond":118,"p95TokensPerSecond":99.12,"samples":5,"estimated":false,"costPerMTokPerSec":0.0038},{"modelId":"gemini-3.6-flash","name":"Gemini 3.6 Flash","provider":"Google","rank":14,"ttftMs":310,"tokensPerSecond":114,"p95TokensPerSecond":93.48,"samples":5,"estimated":false,"costPerMTokPerSec":0.0296},{"modelId":"nova-lite","name":"Amazon Nova Lite","provider":"Amazon","rank":15,"ttftMs":250,"tokensPerSecond":108,"p95TokensPerSecond":95.04,"samples":5,"estimated":false,"costPerMTokPerSec":0.001},{"modelId":"grok-4.20-0309-non-reasoning","name":"Grok-4.20","provider":"xAI","rank":16,"ttftMs":290,"tokensPerSecond":104,"p95TokensPerSecond":91.52,"samples":5,"estimated":false,"costPerMTokPerSec":0.0288},{"modelId":"grok-4.3","name":"Grok 4.3","provider":"xAI","rank":17,"ttftMs":320,"tokensPerSecond":98,"p95TokensPerSecond":82.32,"samples":5,"estimated":false,"costPerMTokPerSec":0.0159},{"modelId":"mistral-medium","name":"Mistral Medium 3","provider":"Mistral","rank":18,"ttftMs":320,"tokensPerSecond":92,"p95TokensPerSecond":73.6,"samples":5,"estimated":false,"costPerMTokPerSec":0.0087},{"modelId":"qwen3.7-plus","name":"Qwen 3.7 Plus","provider":"Qwen","rank":19,"ttftMs":340,"tokensPerSecond":84,"p95TokensPerSecond":75.6,"samples":5,"estimated":false,"costPerMTokPerSec":0.0131},{"modelId":"gpt-5.6-terra","name":"GPT-5.6 Terra","provider":"OpenAI","rank":20,"ttftMs":380,"tokensPerSecond":78,"p95TokensPerSecond":63.96,"samples":5,"estimated":false,"costPerMTokPerSec":0.0577},{"modelId":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","provider":"Anthropic","rank":21,"ttftMs":360,"tokensPerSecond":76,"p95TokensPerSecond":69.92,"samples":5,"estimated":false,"costPerMTokPerSec":0.0789},{"modelId":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"DeepSeek","rank":22,"ttftMs":480,"tokensPerSecond":68,"p95TokensPerSecond":62.56,"samples":5,"estimated":false,"costPerMTokPerSec":0.008},{"modelId":"nova-pro","name":"Amazon Nova Pro","provider":"Amazon","rank":23,"ttftMs":350,"tokensPerSecond":64,"p95TokensPerSecond":55.04,"samples":5,"estimated":false,"costPerMTokPerSec":0.0219},{"modelId":"mistral-large","name":"Mistral Large 3","provider":"Mistral","rank":24,"ttftMs":400,"tokensPerSecond":61,"p95TokensPerSecond":50.02,"samples":5,"estimated":false,"costPerMTokPerSec":0.0492},{"modelId":"claude-opus-4-8","name":"Claude Opus 4.8","provider":"Anthropic","rank":25,"ttftMs":470,"tokensPerSecond":58,"p95TokensPerSecond":53.36,"samples":5,"estimated":false,"costPerMTokPerSec":0.1724},{"modelId":"gemini-3.1-pro","name":"Gemini 3.1 Pro","provider":"Google","rank":26,"ttftMs":420,"tokensPerSecond":55,"p95TokensPerSecond":50.6,"samples":5,"estimated":false,"costPerMTokPerSec":0.0818},{"modelId":"grok-4.20-0309-reasoning","name":"Grok-4.20 Reasoning","provider":"xAI","rank":27,"ttftMs":540,"tokensPerSecond":52,"p95TokensPerSecond":46.8,"samples":5,"estimated":false,"costPerMTokPerSec":0.0577},{"modelId":"qwen3.7-max","name":"Qwen 3.7 Max","provider":"Qwen","rank":28,"ttftMs":460,"tokensPerSecond":49,"p95TokensPerSecond":45.08,"samples":5,"estimated":false,"costPerMTokPerSec":0.0571},{"modelId":"qwen3.8-max","name":"Qwen 3.8 Max","provider":"Qwen","rank":29,"ttftMs":470,"tokensPerSecond":47,"p95TokensPerSecond":37.6,"samples":5,"estimated":false,"costPerMTokPerSec":0.0596},{"modelId":"gpt-5.6-sol","name":"GPT-5.6 Sol","provider":"OpenAI","rank":30,"ttftMs":560,"tokensPerSecond":44,"p95TokensPerSecond":35.64,"samples":5,"estimated":false,"costPerMTokPerSec":0.2557},{"modelId":"claude-fable-5","name":"Claude Fable 5","provider":"Anthropic","rank":31,"ttftMs":610,"tokensPerSecond":41,"p95TokensPerSecond":35.67,"samples":5,"estimated":false,"costPerMTokPerSec":0.4878},{"modelId":"llama-3.1-8b","name":"Llama 3.1 8B","provider":"Groq","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5-nano","name":"GPT-5 Nano","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","provider":"Google","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-4o-mini","name":"GPT-4o Mini","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"grok-3-mini","name":"Grok-3 Mini","provider":"xAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"llama-4-maverick","name":"Llama 4 Maverick","provider":"Groq","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5.4-nano","name":"GPT-5.4 Nano","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","provider":"Google","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"llama-3.3-70b","name":"Llama 3.3 70B","provider":"Groq","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5-mini","name":"GPT-5 Mini","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gemini-2.5-flash","name":"Gemini 2.5 Flash","provider":"Google","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"glm-5.1","name":"GLM-5.1","provider":"Z.ai","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"qwen3.6-27b","name":"Qwen 3.6 27B","provider":"Groq","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5.4-mini","name":"GPT-5.4 Mini","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gemini-3.1-flash","name":"Gemini 3.1 Flash","provider":"Google","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"o3-mini","name":"o3-Mini","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"glm-5.2","name":"GLM-5.2","provider":"Z.ai","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"grok-3","name":"Grok-3","provider":"xAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gemini-3.5-flash","name":"Gemini 3.5 Flash","provider":"Google","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5","name":"GPT-5","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-4.1","name":"GPT-4.1","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-4o","name":"GPT-4o","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5.4","name":"GPT-5.4","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-opus-4-7","name":"Claude Opus 4.7","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-opus-4-6","name":"Claude Opus 4.6","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-opus-4-5","name":"Claude Opus 4.5","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-4-turbo","name":"GPT-4 Turbo","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-opus-4-1","name":"Claude Opus 4.1","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"claude-opus-4","name":"Claude Opus 4","provider":"Anthropic","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null},{"modelId":"gpt-5.4-pro","name":"GPT-5.4 Pro","provider":"OpenAI","rank":null,"ttftMs":null,"tokensPerSecond":null,"p95TokensPerSecond":null,"samples":0,"estimated":false,"costPerMTokPerSec":null}]}