Benchmark

RULER

RULER v1 is a synthetic long-context benchmark for measuring how model quality degrades as input length increases. This packaging follows the public…

Modality
text
Categories
long_context, reasoning
Openness
unknown
Source
llm_stats
Reported scores
4

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Nemotron 3 Super (120B A12B)NVIDIA0.91752026-03-11evidence
Nemotron 3 Ultra (550B A55B)NVIDIA0.9472026-06-04evidence
Phi-3.5-mini-instructMicrosoft0.8412024-08-23evidence
Phi-3.5-MoE-instructMicrosoft0.8712024-08-23evidence

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.