Skip to content

Benchmark

Design Arena Elo (models/dataviz)

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.84

Score distribution

1,179.2
Mean
1,190
Median
102.4
Std dev
1,050
10th percentile
1,300
90th percentile
872
Min
8721,383
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.84 for chat models, measured over 114 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 101–126 of 126 results.