Model card
DINOv2 (ViT-g) + Linear.
Meta AIopen-sourceUnknown paramsSelf-supervised ViT-giant + linear head
Self-supervised vision transformer. 62.0 mIoU on ADE20K with just a linear probe. No fine-tuning needed.
§ 02 · Benchmarks
Every benchmark DINOv2 (ViT-g) + Linear has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ADE20K | Computer Vision · Semantic Segmentation | mIoU | 62.0% | #3 | — | 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 DINOv2 (ViT-g) + Linear actually performs.
§ 05 · Related models
Other Meta AI models scored on Codesota.
GENRE
1 result · 1 SOTA
SeamlessM4T v2 Large
2.3B params · 1 result · 1 SOTA
wav2vec 2.0 Large (960h)
317M params · 3 results
HuBERT Large (LS-960)
317M params · 2 results
Fairseq S2T (MuST-C)
~150M params · 1 result
Mask2Former (Swin-L)
Unknown params · 1 result
MusicGen Large
3.3B params · 1 result
Voicebox
330M params · 1 result
§ 06 · Sources & freshness
Where these numbers come from.
arxiv
1
result
0 of 1 rows marked verified.