Skip to content

Benchmark

AHELM: LibriSpeech - WER

Scores are percentages. Lower is better.

Models measured
12
Scores recorded
12
Sources
1
IQ weight
1.49

Score distribution

9.7%
Mean
7.1%
Median
8.2%
Std dev
4.3%
10th percentile
16.3%
90th percentile
3.9%
Min
3.9%34.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.49 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