Skip to content

Benchmark

ScreenSpot-v2

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

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.30

Score distribution

58.3%
Mean
46.9%
Median
28.1%
Std dev
20.1%
10th percentile
94.9%
90th percentile
20.1%
Min
20.1%94.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.30 for chat models, measured over 5 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)