RULER authors
RULER at a 64K-token context
Synthetic long-context benchmark of retrieval, multi-hop tracing, aggregation and question answering, scored at a 64K-token context.
ModelsModels with a result.2
Top resultBest result on this benchmark.—
Top-3 spreadPoints from first to third.—
YearYear of release.2024
Results
2 results#ModelResultThe score from the source.
