reasoning benchmark
RULER
RULER v1 is a synthetic long-context benchmark for measuring how model quality degrades as input length increases. This packaging follows the public standalone NVIDIA RULER implementation with 13 official tasks spanning retrieval, multi-hop tracing, aggregation, and QA.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
RULER leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | NV | 94.7% | 100.0% | 4 | C | |
| 2 | NV | 91.8% | 66.7% | 4 | C | |
| 3 | MI | 87.1% | 33.3% | 4 | C | |
| 4 | MI | 84.1% | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
RULER highlights
The top published results on this benchmark's own scale.
What is RULER?
Definition and scoring fields from the benchmark registry.
RULER v1 is a synthetic long-context benchmark for measuring how model quality degrades as input length increases. This packaging follows the public standalone NVIDIA RULER implementation with 13 official tasks spanning retrieval, multi-hop tracing, aggregation, and QA.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- RULER
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- ruler|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about RULER.
Which model scores highest on RULER?
Nemotron 3 Ultra (550B A55B) is currently ranked first with 94.7%.
What does RULER measure?
RULER v1 is a synthetic long-context benchmark for measuring how model quality degrades as input length increases. This packaging follows the public standalone NVIDIA RULER implementation with 13 official tasks spanning retrieval, multi-hop tracing, aggregation, and QA.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.