# Image Classification on VLCS (4 Metrics)

Source: [Image Classification on VLCS (4 Metrics)](<https://www.sota2.com/research/sota/image-classification-on-vlcs-4-metrics>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:34:20.291Z

Evaluation of standard Image Classification performance on the VLCS dataset, reporting four distinct accuracy metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification |
| Dataset (including any stated split) | VLCS |
| Metric | Accuracy (Metric 1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy (Metric 1)](<https://www.sota2.com/research/sota/image-classification-on-vlcs-4-metrics.md?metric=Accuracy%20(Metric%201)>): Higher is better; unit: PERCENT.

- [Accuracy (Metric 2)](<https://www.sota2.com/research/sota/image-classification-on-vlcs-4-metrics.md?metric=Accuracy%20(Metric%202)>): Higher is better; unit: PERCENT.

- [Accuracy (Metric 3)](<https://www.sota2.com/research/sota/image-classification-on-vlcs-4-metrics.md?metric=Accuracy%20(Metric%203)>): Higher is better; unit: PERCENT.

- [Accuracy (Metric 4)](<https://www.sota2.com/research/sota/image-classification-on-vlcs-4-metrics.md?metric=Accuracy%20(Metric%204)>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/image-classification-on-vlcs-4-metrics.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Metric 1) | Result date | Report paper |
| --- | --- | --- | --- |
| MVT + FT | 84.2 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT + FT | 84.2 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT | 83.8 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT | 83.8 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT + FT | 83.7 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT | 81.2 | Not recorded | 69535c9a53fdd5c36173db85 |
| Vanilla FT | 78.8 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT + FT | 76.8 | Not recorded | 69535c9a53fdd5c36173db85 |
| Vanilla FT | 75.5 | Not recorded | 69535c9a53fdd5c36173db85 |
| CLIP | 74.9 | Not recorded | 69535c9a53fdd5c36173db85 |
| CLIP | 74.9 | Not recorded | 69535c9a53fdd5c36173db85 |
| EVA | 72.5 | Not recorded | 69535c9a53fdd5c36173db85 |
| MVT | 67.5 | Not recorded | 69535c9a53fdd5c36173db85 |

### MVT + FT

Accuracy (Metric 1): 84.2. Result ID: 6999344b5698665ec49d5b41.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"MLLM":"MMICL","Backbone":"ViT-L"}. This record does not assert independent reproduction.

### MVT + FT

Accuracy (Metric 1): 84.2. Result ID: 6999344b5698665ec49d5b5b.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14"}. This record does not assert independent reproduction.

### MVT

Accuracy (Metric 1): 83.8. Result ID: 6999344b5698665ec49d5b40.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"MLLM":"MMICL","Backbone":"ViT-L"}. This record does not assert independent reproduction.

### MVT

Accuracy (Metric 1): 83.8. Result ID: 6999344b5698665ec49d5b5a.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14"}. This record does not assert independent reproduction.

### MVT + FT

Accuracy (Metric 1): 83.7. Result ID: 6999344b5698665ec49d5b5f.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Backbone":"ViT-g"}. This record does not assert independent reproduction.

### MVT

Accuracy (Metric 1): 81.2. Result ID: 6999344b5698665ec49d5b5e.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Backbone":"ViT-g"}. This record does not assert independent reproduction.

### Vanilla FT

Accuracy (Metric 1): 78.8. Result ID: 6999344b5698665ec49d5b59.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14"}. This record does not assert independent reproduction.

### MVT + FT

Accuracy (Metric 1): 76.8. Result ID: 6999344b5698665ec49d5b43.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"MLLM":"Otter","Backbone":"ViT-L"}. This record does not assert independent reproduction.

### Vanilla FT

Accuracy (Metric 1): 75.5. Result ID: 6999344b5698665ec49d5b5d.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Backbone":"ViT-g"}. This record does not assert independent reproduction.

### CLIP

Accuracy (Metric 1): 74.9. Result ID: 6999344b5698665ec49d5b3f.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"MLLM":"None","Backbone":"ViT-L"}. This record does not assert independent reproduction.

### CLIP

Accuracy (Metric 1): 74.9. Result ID: 6999344b5698665ec49d5b58.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14"}. This record does not assert independent reproduction.

### EVA

Accuracy (Metric 1): 72.5. Result ID: 6999344b5698665ec49d5b5c.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e1b1e209131cea3dd3f.md>)

[Implementation](<https://github.com/baaivision/EVA>)

Recorded evaluation configuration: {"Backbone":"ViT-g"}. This record does not assert independent reproduction.

### MVT

Accuracy (Metric 1): 67.5. Result ID: 6999344b5698665ec49d5b42.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"MLLM":"Otter","Backbone":"ViT-L"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
