Skip to content

Benchmark

AHELM: Multimodal EmotionLines Dataset (MELD) Audio - PEM

Scores are percentages.

Models measured
12
Scores recorded
12
Sources
1
IQ weight
0.00

Score distribution

43.4%
Mean
45.6%
Median
5.6%
Std dev
34%
10th percentile
49.1%
90th percentile
33.4%
Min
33.4%51.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 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