Benchmark Radar™
Star —

FlenQA Benchmark

Explore score history ↗

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

Modality
text
Evaluates
long context, reasoning
Openness
unknown
Importer
LLM Stats

Source provenance

FlenQA results and reported scores

Reported benchmark scores · LLM Stats

Reported scores: 2

ModelOrganizationReported valueReportedEvidence
Phi 4 ReasoningMicrosoft0.9772025-04-30evidence
Phi 4 Reasoning PlusMicrosoft0.9792025-04-30evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite FlenQA?

Related long context, reasoning benchmarks