Skip to content

Benchmark

RULER

Long context benchmarks measure how well models use information in long inputs. Scores are percentages.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

90.9%
Mean
91.8%
Median
2.7%
Std dev
87.1%
10th percentile
94.7%
90th percentile
87.1%
Min
87.1%94.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Nemotron 3 Ultra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.7%
2Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.8%
3Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.1%
4phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.1%

Data credits: Data by LLM Stats