Skip to content

Benchmark

IDP Core Bench - VQA

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

Models measured
24
Scores recorded
24
Sources
1
IQ weight
0.69

Score distribution

62.7%
Mean
64.1%
Median
16.1%
Std dev
52.4%
10th percentile
78.2%
90th percentile
0%
Min
0%85%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.69 for chat models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard