Model card
SegGPT.
BAAISemantic segmentationGeneralist segmentation modelopen1 current SOTA
Headline ADE20K semantic segmentation row in the vision register. Use it as a semantic mIoU reference, not as a universal mask model.
§ 02 · Benchmarks
Every benchmark SegGPT has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ADE20K | Computer vision · Semantic segmentation | mIoU | 62.6% | #1 | 2026-04-22 | 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 SegGPT actually performs.
§ 05 · Related models
Other BAAI models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
Codesota vision register
1
result
1 of 1 rows marked verified.