Codesota · Models · SoViT-400m/14Google DeepMind1 results · 1 benchmarks
Model card

SoViT-400m/14.

Google DeepMindopen-source400M paramsVision Transformer (Shape-Optimized)

Shape-Optimized ViT derived from compute-optimal scaling laws. 400M params, patch14. Pre-trained on WebLI (contrastive + reconstruction head), finetuned on ImageNet-1K at 224px. NeurIPS 2023. Paper: arxiv:2305.13035.

§ 01 · Benchmarks

Every benchmark SoViT-400m/14 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01ImageNet-1KComputer Vision · Image Classificationtop-1-accuracy90.3%#3/20source ↗
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 SoViT-400m/14 actually performs.

Computer Vision
1
benchmark
avg rank #3.0
§ 04 · Related models

Other Google DeepMind models scored on Codesota.

Gemma 3 12B IT
12B params · 2 results
Gemma 3 4B IT
4B params · 2 results
Disco57
1 result
DreamerV3
1 result
Gemini Ultra
Unknown params · 1 result
MEME
1 result
BBF (Bigger, Better, Faster)
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

neurips-2023
1
result
0 of 1 rows marked verified.