Skip to content

Benchmark

IDP Core Bench - KIE

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

Models measured
24
Scores recorded
24
Sources
1
IQ weight
1.88

Score distribution

74.7%
Mean
85.7%
Median
26.6%
Std dev
11.1%
10th percentile
89.5%
90th percentile
0%
Min
0%91.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.88 for chat models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard