# Image Classification on 4-task benchmark (CIFAR100, Flowers, Pets, STL10)

Source: [Image Classification on 4-task benchmark (CIFAR100, Flowers, Pets, STL10)](<https://www.sota2.com/research/sota/image-classification-on-4-task-benchmark-cifar100-flowers-pets-stl10>)

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

Data updated: 2026-03-09T08:22:48.283Z

Evaluation of Image Classification performance across a composite benchmark consisting of CIFAR100, Flowers, Pets, and STL10 datasets.

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) | 4-task benchmark (CIFAR100, Flowers, Pets, STL10) (unseen) |
| Metric | CIFAR100 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [CIFAR100 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-4-task-benchmark-cifar100-flowers-pets-stl10.md?metric=CIFAR100%20Accuracy>): Higher is better; unit: PERCENT.

- [Flowers Accuracy](<https://www.sota2.com/research/sota/image-classification-on-4-task-benchmark-cifar100-flowers-pets-stl10.md?metric=Flowers%20Accuracy>): Higher is better; unit: PERCENT.

- [Pets Accuracy](<https://www.sota2.com/research/sota/image-classification-on-4-task-benchmark-cifar100-flowers-pets-stl10.md?metric=Pets%20Accuracy>): Higher is better; unit: PERCENT.

- [STL10 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-4-task-benchmark-cifar100-flowers-pets-stl10.md?metric=STL10%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/image-classification-on-4-task-benchmark-cifar100-flowers-pets-stl10.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CIFAR100 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Zeroshot | 76.13 | Not recorded | 69ae53e62d603e6de3e4294c |
| DC-Merge | 65.4 | Not recorded | 69ae53e62d603e6de3e4294c |
| Iso-CTS | 61.9 | Not recorded | 69ae53e62d603e6de3e4294c |
| WUDI-Merging | 60.81 | Not recorded | 69ae53e62d603e6de3e4294c |
| TSV-M | 60.79 | Not recorded | 69ae53e62d603e6de3e4294c |
| KnOTS-TIES | 57.5 | Not recorded | 69ae53e62d603e6de3e4294c |
| Task Arithmetic | 57.28 | Not recorded | 69ae53e62d603e6de3e4294c |

### Zeroshot

CIFAR100 Accuracy: 76.13. Result ID: 69ae83436dbb7075b95699c3.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

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

### DC-Merge

CIFAR100 Accuracy: 65.4. Result ID: 69ae83436dbb7075b95699c9.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

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

### Iso-CTS

CIFAR100 Accuracy: 61.9. Result ID: 69ae83436dbb7075b95699c8.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795d1e209131cea7d4a1.md>)

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

### WUDI-Merging

CIFAR100 Accuracy: 60.81. Result ID: 69ae83436dbb7075b95699c6.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795e1e209131cea7d4c8.md>)

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

### TSV-M

CIFAR100 Accuracy: 60.79. Result ID: 69ae83436dbb7075b95699c7.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751d7.md>)

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

### KnOTS-TIES

CIFAR100 Accuracy: 57.5. Result ID: 69ae83436dbb7075b95699c5.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755b1e209131cea676d6.md>)

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

### Task Arithmetic

CIFAR100 Accuracy: 57.28. Result ID: 69ae83436dbb7075b95699c4.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e62d603e6de3e4294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef01e209131cea43012.md>)

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

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