Model card
BEiT-3 (ViT-L).
Microsoftopen-sourceUnknown paramsMultiway Transformer (ViT-L/14)
General-purpose multimodal foundation model. 62.8 mIoU on ADE20K. CVPR 2023.
§ 01 · Benchmarks
Every benchmark BEiT-3 (ViT-L) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ADE20K | Computer Vision · Semantic Segmentation | mIoU | 62.8% | #2 | — | 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.
§ 02 · Strengths by area
Where BEiT-3 (ViT-L) actually performs.
§ 04 · Related models
Other Microsoft models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
0 of 1 rows marked verified.