# Extreme Classification on Amazon-670k

Source: [Extreme Classification on Amazon-670k](<https://www.sota2.com/research/sota/extreme-classification-on-amazon-670k>)

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

Data updated: 2026-02-26T05:29:05.628Z

Evaluation of Extreme Classification performance on the Amazon-670K dataset, measured using 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 | Extreme Classification |
| Dataset (including any stated split) | Amazon-670k |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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](<https://www.sota2.com/research/sota/extreme-classification-on-amazon-670k.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PyTorch-GPU | 34.9 | Not recorded | 68fa70951e209131cea4bffb |
| BOLT Dense Inference (ALN) | 34.8 | Not recorded | 68fa70951e209131cea4bffb |
| Tensorflow-CPU | 34.6 | Not recorded | 68fa70951e209131cea4bffb |
| Tensorflow-GPU | 34.6 | Not recorded | 68fa70951e209131cea4bffb |
| BOLT Sparse Inference (ALN) | 34.5 | Not recorded | 68fa70951e209131cea4bffb |
| PyTorch-CPU | 34.1 | Not recorded | 68fa70951e209131cea4bffb |
| BOLT Dense Inference | 32.5 | Not recorded | 68fa70951e209131cea4bffb |
| BOLT Sparse Inference | 29.8 | Not recorded | 68fa70951e209131cea4bffb |

### PyTorch-GPU

Accuracy: 34.9. Result ID: 699136773a6c3148490684f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

Recorded evaluation configuration: {"Framework":"PyTorch","Hardware":"GPU (NVIDIA A100)","Training Epochs":5,"Inference Time (ms)":0.6}. This record does not assert independent reproduction.

### BOLT Dense Inference (ALN)

Accuracy: 34.8. Result ID: 699136773a6c3148490684ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Implementation](<https://github.com/ThirdAIResearch/BOLT_Benchmarks>)

Recorded evaluation configuration: {"Framework":"BOLT","Inference Mode":"Dense","ALN (Adding Label Neurons)":true,"Hardware":"CPU (AWS c6i.8xlarge)","Training Epochs":5,"Inference Time (ms)":63}. This record does not assert independent reproduction.

### Tensorflow-CPU

Accuracy: 34.6. Result ID: 699136773a6c3148490684f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

Recorded evaluation configuration: {"Framework":"TensorFlow","Hardware":"CPU (AWS c6i.8xlarge)","Training Epochs":5,"Inference Time (ms)":44.4}. This record does not assert independent reproduction.

### Tensorflow-GPU

Accuracy: 34.6. Result ID: 699136773a6c3148490684f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

Recorded evaluation configuration: {"Framework":"TensorFlow","Hardware":"GPU (NVIDIA A100)","Training Epochs":5,"Inference Time (ms)":1.9}. This record does not assert independent reproduction.

### BOLT Sparse Inference (ALN)

Accuracy: 34.5. Result ID: 699136773a6c3148490684ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Implementation](<https://github.com/ThirdAIResearch/BOLT_Benchmarks>)

Recorded evaluation configuration: {"Framework":"BOLT","Inference Mode":"Sparse","ALN (Adding Label Neurons)":true,"Hardware":"CPU (AWS c6i.8xlarge)","Training Epochs":5,"Inference Time (ms)":4.4}. This record does not assert independent reproduction.

### PyTorch-CPU

Accuracy: 34.1. Result ID: 699136773a6c3148490684f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

Recorded evaluation configuration: {"Framework":"PyTorch","Hardware":"CPU (AWS c6i.8xlarge)","Training Epochs":5,"Inference Time (ms)":27.4}. This record does not assert independent reproduction.

### BOLT Dense Inference

Accuracy: 32.5. Result ID: 699136773a6c3148490684f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Implementation](<https://github.com/ThirdAIResearch/BOLT_Benchmarks>)

Recorded evaluation configuration: {"Framework":"BOLT","Inference Mode":"Dense","ALN (Adding Label Neurons)":false,"Hardware":"CPU (AWS c6i.8xlarge)","Training Epochs":5,"Inference Time (ms)":67}. This record does not assert independent reproduction.

### BOLT Sparse Inference

Accuracy: 29.8. Result ID: 699136773a6c3148490684ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70951e209131cea4bffb.md>)

[Implementation](<https://github.com/ThirdAIResearch/BOLT_Benchmarks>)

Recorded evaluation configuration: {"Framework":"BOLT","Inference Mode":"Sparse","ALN (Adding Label Neurons)":false,"Hardware":"CPU (AWS c6i.8xlarge)","Training Epochs":5,"Inference Time (ms)":4}. This record does not assert independent reproduction.

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