Skip to content

Benchmark

Physical AI Bench Understanding BridgeData V2

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

Models measured
15
Scores recorded
17
Sources
1
IQ weight
1.35

Score distribution

40.4%
Mean
38%
Median
6.9%
Std dev
35%
10th percentile
49%
90th percentile
29%
Min
29%57%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.35 for chat models, measured over 15 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: Physical AI Bench (SHI Labs), MIT (licence)