Skip to content

Benchmark

RULER · 256K

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

Models measured
1
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

96.6%
Mean
96.8%
Median
0.265%
Std dev
96.3%
10th percentile
96.8%
90th percentile
96.3%
Min
96.3%96.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Nemotron 3 Super 120B A12Btechnical report Table 5/8 · dedicated RULER container· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.8%
2Nemotron 3 Super 120B A12Bofficial HF model card · dedicated RULER container· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.3%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.