Skip to content

Benchmark

Design Arena Elo (models/multitovideo)

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

Models measured
14
Scores recorded
15
Sources
1
IQ weight
1.89

Score distribution

1,129.3
Mean
1,258
Median
219.8
Std dev
814
10th percentile
1,330
90th percentile
774
Min
7741,348
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.89 for video-generation models, measured over 14 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard