{"benchmark_id":"simpleqa-verified","benchmark_name":"SimpleQA Verified","benchmark_description":"SimpleQA Verified is a curated, reliability-focused subset of SimpleQA that addresses label noise and redundancy in the original benchmark, measuring short-form parametric factual accuracy of large language models on fact-seeking questions with single, indisputable answers.","max_score":1.0,"categories":["reasoning","factuality","general"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"mai-thinking-1","model_name":"MAI-Thinking-1","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.31,"normalized_score":0.31,"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":2,"model_id":"inkling-small","model_name":"Inkling-Small","organization_name":"Thinking Machines Lab","organization_id":"thinking-machines","benchmark_score":0.206,"normalized_score":0.206,"verified":false,"self_reported":true,"provider_id":"thinking-machines","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":256000,"release_date":"2026-07-30","announcement_date":"2026-07-30","multimodal":true,"param_count":276000000000,"is_new":false}]}