Codesota · Models · V-JEPA 2 ViT-g (1B, 384px)3 results · 3 benchmarks
Model card
V-JEPA 2 ViT-g (1B, 384px).
unknown
§ 02 · Benchmarks
Every benchmark V-JEPA 2 ViT-g (1B, 384px) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Something-Something V2 | Computer Vision · Video classification | accuracy | 77.3% | #1 | — | source ↗ |
| 02 | Kinetics-400 | Computer Vision · Video classification | accuracy | 87.3% | #3 | — | source ↗ |
| 03 | ImageNet-1K | Computer Vision · Image Classification | accuracy | 85.1% | #10 | — | source ↗ |
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.
§ 03 · Strengths by area
Where V-JEPA 2 ViT-g (1B, 384px) actually performs.
§ 04 · Papers
1 paper with results for V-JEPA 2 ViT-g (1B, 384px).
- 2025-06-11· 3 results
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
3
results
0 of 3 rows marked verified.