# Image Classification on Fruit-306 (test)

Source: [Image Classification on Fruit-306 (test)](<https://www.sota2.com/research/sota/image-classification-on-fruit-306-test>)

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

Data updated: 2026-05-21T12:05:16.368Z

Evaluation of Image Classification performance on the test split of the Fruit-306 dataset, measured by Top-1 and Top-5 Accuracy.

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) | Fruit-306 (test) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-fruit-306-test.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-fruit-306-test.md?metric=Top-5%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FruitEnsemble | 70.49 | Not recorded | 6a0e9179f984739ed6738a15 |
| DenseNet201 | 68.5 | Not recorded | 6a0e9179f984739ed6738a15 |
| InceptionResnetV2 | 67.34 | Not recorded | 6a0e9179f984739ed6738a15 |
| ResNet50 | 65.03 | Not recorded | 6a0e9179f984739ed6738a15 |
| EfficientNetB7 | 62.83 | Not recorded | 6a0e9179f984739ed6738a15 |
| GoogleNet | 62.4 | Not recorded | 6a0e9179f984739ed6738a15 |
| ViT-B/16 | 59.69 | Not recorded | 6a0e9179f984739ed6738a15 |
| VGG16 | 58.6 | Not recorded | 6a0e9179f984739ed6738a15 |
| Xception | 58.3 | Not recorded | 6a0e9179f984739ed6738a15 |
| CONVT | 58.02 | Not recorded | 6a0e9179f984739ed6738a15 |
| Qwen-VL-Plus | 56.38 | Not recorded | 6a0e9179f984739ed6738a15 |
| Beit large | 53.73 | Not recorded | 6a0e9179f984739ed6738a15 |
| RVT | 53.47 | Not recorded | 6a0e9179f984739ed6738a15 |
| NasnetLarge | 22.28 | Not recorded | 6a0e9179f984739ed6738a15 |
| Inceptionv3 | 16.35 | Not recorded | 6a0e9179f984739ed6738a15 |

### FruitEnsemble

Top-1 Accuracy: 70.49. Result ID: 6a0ef3b5fbc373592c075939.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

Recorded evaluation configuration: {"Latency (ms)":"19.8‡"}. This record does not assert independent reproduction.

### DenseNet201

Top-1 Accuracy: 68.5. Result ID: 6a0ef3b5fbc373592c075932.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Params (M)":"20.0","FLOPs (G)":"4.4","Latency (ms)":"18.2"}. This record does not assert independent reproduction.

### InceptionResnetV2

Top-1 Accuracy: 67.34. Result ID: 6a0ef3b5fbc373592c07592f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62b91e209131ce9fae18.md>)

Recorded evaluation configuration: {"Params (M)":"55.9","FLOPs (G)":"13.2","Latency (ms)":"25.6"}. This record does not assert independent reproduction.

### ResNet50

Top-1 Accuracy: 65.03. Result ID: 6a0ef3b5fbc373592c075931.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"Params (M)":"25.6","FLOPs (G)":"4.1","Latency (ms)":"12.5"}. This record does not assert independent reproduction.

### EfficientNetB7

Top-1 Accuracy: 62.83. Result ID: 6a0ef3b5fbc373592c075933.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684f1e209131cea1b521.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet>)

Recorded evaluation configuration: {"Params (M)":"66.3","FLOPs (G)":"37.0","Latency (ms)":"45.6"}. This record does not assert independent reproduction.

### GoogleNet

Top-1 Accuracy: 62.4. Result ID: 6a0ef3b5fbc373592c07592b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61801e209131ce9f4ab4.md>)

Recorded evaluation configuration: {"Params (M)":"6.8","FLOPs (G)":"1.5","Latency (ms)":"8.2"}. This record does not assert independent reproduction.

### ViT-B/16

Top-1 Accuracy: 59.69. Result ID: 6a0ef3b5fbc373592c075934.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Params (M)":"86.6","FLOPs (G)":"17.6","Latency (ms)":"32.4"}. This record does not assert independent reproduction.

### VGG16

Top-1 Accuracy: 58.6. Result ID: 6a0ef3b5fbc373592c07592c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61d01e209131ce9f62f5.md>)

[Implementation](<http://www.robots.ox.ac.uk/~vgg/research/very_deep/>)

Recorded evaluation configuration: {"Params (M)":"138.0","FLOPs (G)":"15.5","Latency (ms)":"22.4"}. This record does not assert independent reproduction.

### Xception

Top-1 Accuracy: 58.3. Result ID: 6a0ef3b5fbc373592c07592e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63371e209131ce9fd796.md>)

[Implementation](<https://keras.io/applications/#xception>)

Recorded evaluation configuration: {"Params (M)":"22.9","FLOPs (G)":"8.4","Latency (ms)":"16.5"}. This record does not assert independent reproduction.

### CONVT

Top-1 Accuracy: 58.02. Result ID: 6a0ef3b5fbc373592c075935.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69981e209131cea22ed1.md>)

[Implementation](<https://github.com/leoxiaobin/CvT>)

Recorded evaluation configuration: {"Params (M)":"28.4","FLOPs (G)":"6.2","Latency (ms)":"15.8"}. This record does not assert independent reproduction.

### Qwen-VL-Plus

Top-1 Accuracy: 56.38. Result ID: 6a0ef3b5fbc373592c075938.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

Recorded evaluation configuration: {"Params (M)":"API","FLOPs (G)":"API","Latency (ms)":"1250†"}. This record does not assert independent reproduction.

### Beit large

Top-1 Accuracy: 53.73. Result ID: 6a0ef3b5fbc373592c075936.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d5a1e209131cea39630.md>)

[Implementation](<https://aka.ms/beit>)

Recorded evaluation configuration: {"Params (M)":"304.0","FLOPs (G)":"63.4","Latency (ms)":"55.2"}. This record does not assert independent reproduction.

### RVT

Top-1 Accuracy: 53.47. Result ID: 6a0ef3b5fbc373592c075937.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b4c1e209131cea2d62e.md>)

Recorded evaluation configuration: {"Params (M)":"102.5","FLOPs (G)":"24.1","Latency (ms)":"36.5"}. This record does not assert independent reproduction.

### NasnetLarge

Top-1 Accuracy: 22.28. Result ID: 6a0ef3b5fbc373592c075930.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64441e209131cea039e2.md>)

Recorded evaluation configuration: {"Params (M)":"88.9","FLOPs (G)":"23.6","Latency (ms)":"38.2"}. This record does not assert independent reproduction.

### Inceptionv3

Top-1 Accuracy: 16.35. Result ID: 6a0ef3b5fbc373592c07592d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e9179f984739ed6738a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62331e209131ce9f8333.md>)

Recorded evaluation configuration: {"Params (M)":"23.8","FLOPs (G)":"5.7","Latency (ms)":"14.1"}. This record does not assert independent reproduction.

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