Skip to content

Benchmark

HELM Long Context: RULER HotPotQA - RULER String Match

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

Models measured
11
Scores recorded
11
Sources
1
IQ weight
1.25

Score distribution

51.9%
Mean
55%
Median
10.4%
Std dev
37%
10th percentile
64%
90th percentile
35%
Min
35%70%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.25 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance