Skip to content

Benchmark

OCRVQA

OCR benchmarks measure how well models read text in images and documents. Scores are percentages.

Models measured
17
Scores recorded
17
Sources
1
IQ weight
0.33

Score distribution

33.2%
Mean
27.6%
Median
20%
Std dev
13.5%
10th percentile
60.2%
90th percentile
2.9%
Min
2.9%73.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.33 for chat models, measured over 17 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: OpenVLM Leaderboard (OpenCompass / VLMEvalKit), Apache-2.0 (licence)