Codesota · Computer Vision · Image Classification · ImageNet-V2Tasks/Computer Vision/Image Classification
Image Classification · benchmark dataset · 2019 · EN

ImageNet-V2 Matched Frequency.

10K new test images following ImageNet collection process. Tests model generalization beyond the original test set.

Saturated benchmark

Benchmark near ceiling or stagnant — no meaningful SOTA movement in 2+ years

Paper ↗Submit a result ↵
§ 01 · Leaderboard

Best published scores.

6 results indexed across 2 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary
top-1-accuracy · higher is better
All metrics
accuracy, top-1-accuracy
accuracy
4 rows
#ModelOrgSubmittedPaper / codeaccuracy
01DINOv3 (7B)—Aug 2025DINOv3 · code81.40
02SigLIP 2 (g/16)—Feb 2025SigLIP 2: Multilingual Vision-Language Encoders with Imp… · code79.80
03ALIGN—Feb 2021Scaling Up Visual and Vision-Language Representation Lea… · code70.10
04AltCLIP—Nov 2022AltCLIP: Altering the Language Encoder in CLIP for Exten… · code68.20
top-1-accuracy· primary
2 rows
#ModelOrgSubmittedPaper / codetop-1-accuracy
01Swin Transformer V2 LargeOpenMicrosoftDec 2025microsoft-research84
02ConvNeXt V2 HugeOpenMetaDec 2025meta-research80.50
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

1 steps
of state of the art.

Each row below marks a model that broke the previous record on top-1-accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · top-1-accuracy
  1. Dec 18, 2025Swin Transformer V2 LargeMicrosoft84
Fig 3 · SOTA-setting models only. 1 entries span Dec 2025 → Dec 2025.
§ 04 · Literature

4 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies