Skip to content

Benchmark

OlmOCR Bench - Long/Tiny

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

Models measured
25
Scores recorded
25
Sources
1
IQ weight
0.87

Score distribution

61.1%
Mean
73.8%
Median
29.4%
Std dev
10%
10th percentile
88.9%
90th percentile
0%
Min
0%90.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.87 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