Model card
OpenCLIP ViT-G/14.
LAIONImage-text retrievalCLIP ViT-G/14open
OpenCLIP large ViT model for image-text retrieval. Good starting point when you need open visual embeddings and can run a large encoder.
§ 02 · Benchmarks
Every benchmark OpenCLIP ViT-G/14 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | imagenet-zero-shot | — | top-1 | 80.1% | #3 | 2026-04-20 | 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.
§ 06 · Sources & freshness
Where these numbers come from.
codesota-api
1
result
1 of 1 rows marked verified.