Skip to content

Benchmark

ScreenSpot Pro - Scientific

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

Models measured
8
Scores recorded
10
Sources
1
IQ weight
0.41

Score distribution

35.7%
Mean
31.1%
Median
26.6%
Std dev
2.4%
10th percentile
64.6%
90th percentile
1.2%
Min
1.2%81.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.41 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: ScreenSpot grounding leaderboard (GUI-Agent), Apache-2.0 (licence)