Codesota · Models · olmOCR v0.3.0Allen AI2 results · 1 benchmarks
Model card

olmOCR v0.3.0.

Allen AIopen-sourceOCR Pipeline

Earlier version of olmOCR.

§ 01 · Benchmarks

Every benchmark olmOCR v0.3.0 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01olmOCR-BenchComputer Vision · Document Parsingheaders-footers95.1%#2/4source ↗
02olmOCR-BenchComputer Vision · Document Parsingold-scans-math79.9%#4/4source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where olmOCR v0.3.0 actually performs.

Computer Vision
1
benchmark
avg rank #3.0
§ 04 · Related models

Other Allen AI models scored on Codesota.

olmOCR v0.4.0
9 results
olmOCR-7B
1 result
§ 05 · Sources & freshness

Where these numbers come from.

github-readme
2
results
0 of 2 rows marked verified.