Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Benchmark · ImageNet-V2Home/Leaderboards/Vision & Documents/Image Classification/ImageNet-V2
Unknown

ImageNet-V2.

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

Paper Leaderboard
§ 01 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result Report issue

top-1-accuracy

Top 1 Accuracy is the reported evaluation metric for ImageNet-V2. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for top-1-accuracyverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksEdit
01Swin Transformer V2 Large
SOTA on ImageNet-V2. Tests generalization.
unverified842025Source ↗Edit result
02swin-v2-large
SOTA on ImageNet-V2. Tests generalization.
paper842025Source ↗Edit result
03ConvNeXt V2 Huge
Strong generalization to new test images.
unverified80.52025Source ↗Edit result
04convnext-v2-huge
Strong generalization to new test images.
paper80.52025Source ↗Edit result

Accuracy

Accuracy is the reported evaluation metric for ImageNet-V2. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Accuracyverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksEdit
01DINOv3 (7B)unverified81.42025Paper ↗Code ↗Edit result
02SigLIP 2 (g/16)unverified79.82025Paper ↗Code ↗Edit result
03ALIGNunverified70.12021Paper ↗Code ↗Edit result
04AltCLIPunverified68.22022Paper ↗Code ↗Edit result
§ 04 · Submit a result

Add to the leaderboard.

← Back to Image Classification