Benchmark

Robust IF

Robust IF evaluates instruction-following robustness on diverse, hard prompts, measuring whether a model reliably adheres to constraints across…

Modality
text
Categories
reasoning, instruction_following
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
MAI-Code-1-FlashMicrosoft0.6122026-06-02evidence

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.