New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
RULER benchmark
AI model leaderboard for the RULER benchmark. Compare how large language models score on RULER, see the full ranking, and understand what this AI benchmark measures. Kimi Linear currently leads with 84.3%. Synthetic long-context benchmark probing retrieval, multi-hop, and aggregation at varying lengths.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Kimi Linear | Moonshot | 84.3% | long-context-128k | official ↗ |
| #2 | NVIDIA-Nemotron-Nano-9B-v2 | NVIDIA | 78.9% | from-hf-readme | official ↗ |
Frequently asked questions about RULER
What is the RULER benchmark?
Synthetic long-context benchmark probing retrieval, multi-hop, and aggregation at varying lengths.
How is the RULER benchmark scored?
RULER is scored using the accuracy (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on RULER?
As of the latest reported scores on GenAIList, Kimi Linear achieves the highest result on RULER with a score of 84.3%.
Is a higher RULER score better?
Yes. On RULER a higher score indicates better performance, so models near the top of the leaderboard are the strongest.