ImageNet Large Scale Visual Recognition Challenge (ILSVRC): the standard 1,000-class image classification benchmark. Sparked the deep learning revolution from 2010 onward.
Top 5 Accuracy is the reported evaluation metric for ImageNet. 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
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | SENet | verified | 97.75 | 2017 | Source ↗ | Looks wrong? |
| 02 | ResNet-152 | verified | 96.43 | 2015 | Source ↗ | Looks wrong? |
| 03 | GoogLeNet | verified | 93.3 | 2014 | Source ↗ | Looks wrong? |
| 04 | AlexNet | verified | 83.6 | 2012 | Source ↗ | Looks wrong? |
| 05 | NEC-UIUC | verified | 71.8 | 2010 | Source ↗ | Looks wrong? |
Top 1 Accuracy is the reported evaluation metric for ImageNet. 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
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | CoCa (ViT-G/14) | verified | 91 | 2022 | Paper ↗ | Looks wrong? |
| 02 | SoViT-400M/14 | verified | 90.3 | 2023 | Source ↗ | Looks wrong? |
| 03 | EVA-02 (ViT-L/14+) | verified | 90 | 2023 | Paper ↗ | Looks wrong? |
| 04 | ViT-22B/14 | verified | 89.51 | 2023 | Source ↗ | Looks wrong? |
| 05 | InternViT-6B (InternVL) | verified | 88.2 | 2024 | Paper ↗ | Looks wrong? |
| 06 | maxvit_base_tf_512.in1k | verified | 86.598 | 2023 | Source ↗ | Looks wrong? |
| 07 | coatnet_2_rw_224.sw_in12k_ft_in1k | verified | 86.58 | 2022 | Source ↗ | Looks wrong? |
| 08 | nextvit_large.bd_ssld_6m_in1k_384 | verified | 86.542 | 2022 | Source ↗ | Looks wrong? |
| 09 | swin_large.ms_in22k_ft_in1k | verified | 86.33 | 2021 | Paper ↗ | Looks wrong? |
| 10 | convnext_base.fb_in22k_ft_in1k | verified | 86.298 | 2022 | Source ↗ | Looks wrong? |