Skip to content

Benchmark

AHELM: Knowledge - Mean win rate

Scores are percentages. Higher is better.

Models measured
12
Scores recorded
12
Sources
1
IQ weight
1.20

Score distribution

56%
Mean
62.5%
Median
21.8%
Std dev
21.9%
10th percentile
81.3%
90th percentile
21.9%
Min
21.9%87.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.20 for chat models, measured over 9 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard