Codesota · Models · GOT-OCR2.0Alibaba3 results · 1 benchmarks
Model card

GOT-OCR2.0.

Alibabamultimodalapache-2.0

General OCR Theory model v2, end-to-end OCR system supporting scene text, formatted documents, and fine-grained OC results.

§ 01 · Benchmarks

Every benchmark GOT-OCR2.0 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CC-OCRComputer Vision · General OCR Capabilitiesdocument-parsing39.2%#5/6source ↗
02CC-OCRComputer Vision · General OCR Capabilitiesmulti-scene-f161.0%#6/9source ↗
03CC-OCRComputer Vision · General OCR Capabilitiesmultilingual-f124.9%#8/8source ↗
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 GOT-OCR2.0 actually performs.

Computer Vision
1
benchmark
avg rank #6.3
§ 04 · Related models

Other Alibaba models scored on Codesota.

Qwen2-VL 72B
4 results
Qwen2.5-72B-Instruct
72B params · 4 results
Qwen2.5-Coder 32B
32B params · 4 results
Qwen 3 72B
72B params · 2 results
Qwen2.5-VL 32B
2 results
Qwen2.5-VL 72B
72B params · 2 results
Qwen 3 14B
14B params · 1 result
Qwen2-VL 7B
7B params · 1 result
§ 05 · Sources & freshness

Where these numbers come from.

cc-ocr-paper
3
results
3 of 3 rows marked verified.