RULER
A synthetic long-context benchmark of 13 tasks across retrieval, multi-hop tracing, aggregation, and QA that measures a model's effective context length by evaluating accuracy at increasing input lengths (4K to 128K+ tokens).
What this benchmark measures
A synthetic long-context benchmark of 13 tasks across retrieval, multi-hop tracing, aggregation, and QA that measures a model's effective context length by evaluating accuracy at increasing input lengths (4K to 128K+ tokens).
Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.
The metric shown here is accuracy. It should be interpreted within RULER, not compared as part of a site-wide ranking.