Skip to content

Benchmark

ViDoRe(v3)

Vision benchmarks measure how well models understand images. Scores are percentages.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
1.80

Score distribution

53.9%
Mean
57.7%
Median
6%
Std dev
45.6%
10th percentile
60.2%
90th percentile
45.6%
Min
45.6%60.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.80 for embedding models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard