Codesota · OCR · Benchmarks · parsebenchHome/OCR/Benchmarks/parsebench
Unknown

parsebench.

OCR benchmark

§ 01 · accuracy

accuracy.

Higher is better

#ModelScoreSource
★
LlamaParse Agentic
Fetched from CodeSOTA API on 2026-04-20
84.9codesota-api
2
LlamaParse Cost Effective
Fetched from CodeSOTA API on 2026-04-20
71.9codesota-api
3
Google Gemini 3 Flash
Fetched from CodeSOTA API on 2026-04-20
71codesota-api
4
Reducto
Fetched from CodeSOTA API on 2026-04-20
67.8codesota-api
5
Qwen 3 VL
Fetched from CodeSOTA API on 2026-04-20
62codesota-api
6
Azure Document Intelligence
Fetched from CodeSOTA API on 2026-04-20
59.6codesota-api
7
Extend
Fetched from CodeSOTA API on 2026-04-20
55.8codesota-api
8
Dots OCR 1.5
Fetched from CodeSOTA API on 2026-04-20
55.8codesota-api
9
Docling
Fetched from CodeSOTA API on 2026-04-20
50.6codesota-api
10
Google Cloud Document AI
Fetched from CodeSOTA API on 2026-04-20
50.4codesota-api
11
AWS Textract
Fetched from CodeSOTA API on 2026-04-20
47.9codesota-api
12
OpenAI GPT-5 Mini
Fetched from CodeSOTA API on 2026-04-20
46.8codesota-api
13
LandingAI
Fetched from CodeSOTA API on 2026-04-20
45.2codesota-api
14
Anthropic Haiku 4.5
Fetched from CodeSOTA API on 2026-04-20
45.2codesota-api
§ Related · Explore

More OCR content.

Verified Model Reviews
Comparisons & Guides
View all OCR benchmarks →← Back to All Benchmarks