Codesota · Models · ConvNeXt V2 HugeMeta2 results · 2 benchmarks
Model card

ConvNeXt V2 Huge.

Metaopen-source650M paramsCNNMIT

88.9% on ImageNet. Best pure ConvNet.

§ 01 · Benchmarks

Every benchmark ConvNeXt V2 Huge has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01ImageNet-V2Computer Vision · Image Classificationtop-1-accuracy80.5%#2/2source ↗
02ImageNet-1KComputer Vision · Image Classificationtop-1-accuracy88.9%#5/20source ↗
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.
§ 02 · Strengths by area

Where ConvNeXt V2 Huge actually performs.

Computer Vision
2
benchmarks
avg rank #3.5
§ 04 · Related models

Other Meta models scored on Codesota.

DeiT-B Distilled
86M params · 2 results · 1 SOTA
Llama 3 70B
8 results
Llama 3.1 405B
6 results
Llama-4-Maverick
400B total / 17B active (128 experts) params · 6 results
Llama 3.1 70B
4 results
Code Llama 34B
Unknown params · 2 results
CodeLlama 70B
70B params · 1 result
ConvNeXt V2 Base
89M params · 1 result
§ 05 · Sources & freshness

Where these numbers come from.

meta-research
2
results
0 of 2 rows marked verified.