Skip to content

Benchmark

HELM Long Context: OpenAI MRCR - MRCR Accuracy

Scores are percentages. Higher is better.

Models measured
11
Scores recorded
11
Sources
1
IQ weight
1.05

Score distribution

18.2%
Mean
17.9%
Median
4.5%
Std dev
11.1%
10th percentile
21.6%
90th percentile
9.9%
Min
9.9%25.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.05 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