Codesota · Models · Swin Transformer V2 LargeMicrosoft1 results · 1 benchmarks
Model card

Swin Transformer V2 Large.

Microsoftopen-source197M paramsHierarchical Vision TransformerMIT1 current SOTA

86.8% on Kinetics-400. Scales to 3B parameters.

§ 01 · Benchmarks

Every benchmark Swin Transformer V2 Large has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01ImageNet-V2Computer Vision · Image Classificationtop-1-accuracy84.0%#1/2source ↗
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 Swin Transformer V2 Large actually performs.

Computer Vision
1
benchmark
avg rank #1.0 · 1 SOTA
§ 04 · Related models

Other Microsoft models scored on Codesota.

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

Where these numbers come from.

microsoft-research
1
result
0 of 1 rows marked verified.