Skip to content

Benchmark

MedHELM: BMT-Status - EM

Scores are percentages. Higher is better.

Models measured
13
Scores recorded
13
Sources
1
IQ weight
0.19

Score distribution

81.1%
Mean
80.5%
Median
4.2%
Std dev
77.3%
10th percentile
87.3%
90th percentile
74.1%
Min
74.1%90%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.19 for chat models, measured over 13 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