Skip to content

Benchmark

ScreenSpot Pro

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

Models measured
34
Scores recorded
54
Sources
4
IQ weight
1.42

Score distribution

64.4%
Mean
69.1%
Median
22.8%
Std dev
26.8%
10th percentile
87.6%
90th percentile
0.82%
Min
0.82%92.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.42 for chat models, measured over 34 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51qwen2.5-vl-3b-instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
16.1%
52GPT 5resized, high· ScreenSpot data6%
53Qwen2-VL (72B) Instruct· ScreenSpot data1%
54GPT 4o· ScreenSpot data0.82%

Showing 51–54 of 54 results.

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · ScreenSpot grounding leaderboard (GUI-Agent), Apache-2.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark