{"benchmark_id":"flenqa","name":"FlenQA","parent_benchmark":null,"categories":["reasoning","long_context"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","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","paper_link":"https://arxiv.org/abs/2402.14848","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.214382+00:00","updated_at":"2026-07-05T18:27:48.010797+00:00","statistics":{"total_models":2,"average_score":0.978,"min_score":0.977,"max_score":0.979,"score_stddev":0.0014142135623730963,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-4-reasoning-plus","model_name":"Phi 4 Reasoning Plus","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.979,"normalized_score":0.979,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-4-reasoning-plus","analysis_method":"3K-token subset","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-04-30","param_count":14000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"phi-4-reasoning","model_name":"Phi 4 Reasoning","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.977,"normalized_score":0.977,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-4-reasoning-plus","analysis_method":"3K-token subset","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-04-30","param_count":14000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}