Codesota · Models · Florence-2-LargeMicrosoft2 results · 1 benchmarks
Model card

Florence-2-Large.

Microsoftmultimodalmit

Microsoft Florence-2 large vision-language model with unified representation for diverse vision tasks.

§ 01 · Benchmarks

Every benchmark Florence-2-Large has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CC-OCRComputer Vision · General OCR Capabilitiesmultilingual-f149.7%#5/8source ↗
02CC-OCRComputer Vision · General OCR Capabilitiesmulti-scene-f149.2%#8/9source ↗
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 Florence-2-Large actually performs.

Computer Vision
1
benchmark
avg rank #6.5
§ 04 · Related models

Other Microsoft models scored on Codesota.

RAD-DINO
2 results · 1 SOTA
NaturalSpeech 3
~500M params · 1 result · 1 SOTA
Swin Transformer V2 Large
197M params · 1 result · 1 SOTA
WavLM Large (SV)
316M params · 1 result · 1 SOTA
ResNet-50
25M params · 3 results
KOSMOS-2.5
2 results
ResNet-152
60M params · 2 results
Azure OCR
1 result
§ 05 · Sources & freshness

Where these numbers come from.

cc-ocr-paper
2
results
2 of 2 rows marked verified.