{"benchmark_id":"flenqa","benchmark_name":"FlenQA","benchmark_description":"Flexible Length Question Answering dataset for evaluating the impact of input length on reasoning performance of language models, featuring True/False questions embedded in contexts of varying lengths (250-3000 tokens) across three reasoning tasks: Monotone Relations, People In Rooms, and simplified Ruletaker","max_score":1.0,"categories":["long_context","reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"phi-4-reasoning-plus","model_name":"Phi 4 Reasoning Plus","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.979,"normalized_score":0.979,"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":2,"model_id":"phi-4-reasoning","model_name":"Phi 4 Reasoning","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.977,"normalized_score":0.977,"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}]}