Skip to content

Benchmark

RULER Avg

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

Models measured
26
Scores recorded
26
Sources
1
IQ weight
No weight published

Score distribution

83%
Mean
87.5%
Median
12.7%
Std dev
66.2%
10th percentile
95%
90th percentile
50.3%
Min
50.3%96%
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

ModelScore
C4AI Command R 08 2024Command-R-0824, 32B· RULER official results data88.9%
DBRX-instructDBRX, 36B/132B· RULER official results data56.3%
Gemini 1.5 ProGemini-1.5-pro· RULER official results data95.8%
GPT 4 1106 PreviewGPT-4-1106-preview· RULER official results data91.6%
Jamba 1.5 LargeJamba-1.5-large, 94B/398B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.96%
Jamba 1.5 MiniJamba-1.5-mini, 12B/52B· RULER official results data93.9%
Llama 3.1 70B InstructLlama3.1, 70B· RULER official results data89.6%
Llama 3.1 8B InstructLlama3.1, 8B· RULER official results data88.3%
Llama-2-7B-32K-InstructTogether, 7B· RULER official results data50.3%
Mistral 7B Instruct v0.2Mistral, 7B· RULER official results data68.4%
Mistral Large Instruct 2411Mistral-Large-2411, 123B· RULER official results data86%
Mistral NemoMistral-Nemo· RULER official results data66.2%
Mistral-Large-Instruct-2407Mistral-Large-2407, 123B· RULER official results data80.5%
Mixtral 8x22B Instruct v0.1Mixtral-8x22B, 39B/141B· RULER official results data81.9%
Mixtral 8x7B Instruct v0.1Mixtral-8x7B, 12.9B/46.7B· RULER official results data80.4%
Phi-3 Medium 128K InstructPhi3-medium, 14B· RULER official results data81.5%
Phi-3 Mini 128K InstructPhi3-mini, 3.8B· RULER official results data84.8%
Qwen 3 235B A22BQwen3-235B-A22B, 235B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.95%
Qwen1.5-72B-ChatQwen1.5, 72B· RULER official results data55.7%
Qwen2 72B InstructQwen2, 72B· RULER official results data85.9%
Qwen3 14BQwen3-14B, 14B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.94.6%
Qwen3 30B A3BQwen3-30B-A3B, 30B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.91.6%
Qwen3 32BQwen3-32B, 32B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.93.7%
Qwen3 4BQwen3-4B, 4B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.85.2%
Qwen3 8BQwen3-8B, 8B· RULER official results data· Reported by the model's developer. The source relaying it did not verify it.89.1%
Yi-34BYi, 34B, 200k· RULER official results data87.5%

Data credits: NVIDIA RULER, Hsieh et al. Official README numeric table; no separate results licence asserted.