Model card
CLIP ViT-L/14.
OpenAIImage-text retrievalCLIP ViT-L/14open
Canonical CLIP large model. Useful as a baseline for visual retrieval and compatibility with existing CLIP-based tooling.
§ 02 · Benchmarks
Every benchmark CLIP ViT-L/14 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ImageNet Linear Probe | Vision & Documents · Image Classification | top-1-accuracy | 85.3% | #3 | 2026-04-20 | source ↗ |
| 02 | imagenet-zero-shot | — | top-1 | 75.5% | #4 | 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.
§ 03 · Strengths by area
Where CLIP ViT-L/14 actually performs.
§ 05 · Related models
Other OpenAI models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
codesota-api
2
results
2 of 2 rows marked verified.