long context benchmark
RULER 64k Leaderboard
RULER 64k evaluates the official 13-task RULER v1 suite at a 65536-token context budget.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
RULER 64k Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score92.65% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelIB | Score89.96% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelIB | Score80.99% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelIB | Score67.52% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
RULER 64k Highlights
The leading models and scores on this benchmark.
RULER 64k Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for RULER 64k
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is RULER 64k?
What RULER 64k measures and how its scores work.
RULER 64k is a long-context benchmark based on the official 13-task RULER v1 suite.
It reports Score as a ratio for evaluation at a 65536-token context budget.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- RULER 64k
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about RULER 64k.
Which model scores highest on RULER 64k?
MiniCPM-SALA is currently ranked first with 92.65%.
What are the top three models on RULER 64k?
The current leaders are MiniCPM-SALA (92.65%), IBM Granite 4.2 30B (89.96%), and IBM Granite 4.2 8B (80.99%).
Which RULER 64k model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among RULER 64k results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.