# ImageNet-V2

ImageNet-V2 is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Retests ImageNet classifiers on three independently collected 10,000-image test sets matched to the original distribution.

## Details

- Address: Online, Global
- Website: [github.com/modestyachts/ImageNetV2](<https://github.com/modestyachts/ImageNetV2>)
- Tags: Science, Helpful
- Category: Multimodal
- Status: Active
- Data licence: unknown
- Data access: open
- Grader: exact
- Organization: UC Berkeley
- Released: 2019-02
- Paper: [arxiv.org/abs/1902.10811](<https://arxiv.org/abs/1902.10811>)
- Repository: [github.com/modestyachts/ImageNetV2](<https://github.com/modestyachts/ImageNetV2>)
- Task count: 30,000
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is ImageNet-V2?

ImageNet-V2 is at Online, Global.

### How do I contact ImageNet-V2?

To contact ImageNet-V2, visit https://github.com/modestyachts/ImageNetV2.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/imagenet-v2>)
- [Multimodal in Online](<https://aibenchmarkindex.com/global/online/category/multimodal.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.