Categoryexternal
MeasureReported score by context length
Tasks13 tasks in the original author cohort; IBM task count undisclosed
Selected original RULER context sweeps and separate IBM Granite 4.2 reports. The table keeps each source cohort and context length explicit; 128K is the displayed score, and the results do not enter rankings.
No model in the catalog has a published RULER score.The benchmark is defined by RULER: What's the Real Context Size of Your Long-Context Language Models?, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About RULER
What the benchmark measures and how its value is published, from the source’s own record.
What is RULER?
RULER (RULER context-length reports) is an external benchmark published by RULER: What's the Real Context Size of Your Long-Context Language Models. Selected original RULER context sweeps and separate IBM Granite 4.2 reports. The table keeps each source cohort and context length explicit; 128K is the displayed score, and the results do not enter rankings. Its evaluation set is described by the source as 13 tasks in the original author cohort; IBM task count undisclosed.
How is RULER scored?
Each model's result is published by RULER: What's the Real Context Size of Your Long-Context Language Models as reported score by context length. ModelScale prints that value to 2 decimal places, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale