Codesota · Models · DiT-LargeMicrosoft1 results · 1 benchmarks
Model card

DiT-Large.

Microsoftopen-sourceUnknown paramsDocument Image Transformer Large

Self-supervised pre-trained document image transformer. Strong layout detection.

§ 01 · Benchmarks

Every benchmark DiT-Large has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01DocLayNetComputer Vision · Document UnderstandingmAP79.5%#3/7source ↗
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 DiT-Large actually performs.

Computer Vision
1
benchmark
avg rank #3.0
§ 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
Florence-2-Large
2 results
KOSMOS-2.5
2 results
ResNet-152
60M params · 2 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
1
result
0 of 1 rows marked verified.