Codesota · Models · KOSMOS-2.5Microsoft2 results · 1 benchmarks
Model card

KOSMOS-2.5.

Microsoftmultimodalms-research

Microsoft KOSMOS-2.5 multimodal literate model for machine reading of text-intensive images.

§ 02 · Benchmarks

Every benchmark KOSMOS-2.5 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CC-OCRComputer Vision · General OCR Capabilitiesmultilingual-f136.2%#7/8—source ↗
02CC-OCRComputer Vision · General OCR Capabilitiesmulti-scene-f147.5%#9/9—source ↗
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.
§ 03 · Strengths by area

Where KOSMOS-2.5 actually performs.

Computer Vision
1
benchmark
avg rank #8.0
§ 05 · Related models

Other Microsoft models scored on Codesota.

Phi-4
14B params · 17 results
Phi-4 Multimodal Instruct
6B params · 9 results
WizardLM-2-8x22b
7 results
DeBERTa-v3-large
304M params · 6 results
E5-Mistral-7B-instruct
7B params · 4 results
ResNet-152
60M params · 3 results
ResNet-50
25M params · 3 results
UniXcoder
Unknown params · 3 results
§ 06 · Sources & freshness

Where these numbers come from.

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