# E-commerce Search Relevance Classification on Gold Benchmark Offline (offline)

Source: [E-commerce Search Relevance Classification on Gold Benchmark Offline (offline)](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline>)

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

Data updated: 2026-04-07T07:29:27.887Z

Evaluation of E-commerce search relevance classification performance on the Gold Benchmark Offline dataset, reporting per-class F1 scores (C1-C4), Macro F1, and overall 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 | E-commerce search relevance classification |
| Dataset (including any stated split) | Gold Benchmark Offline |
| Metric | C1 F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [C1 F1 Score](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline.md?metric=C1%20F1%20Score>): Higher is better; unit: PERCENT.

- [C2 F1 Score](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline.md?metric=C2%20F1%20Score>): Higher is better; unit: PERCENT.

- [C3 F1 Score](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline.md?metric=C3%20F1%20Score>): Higher is better; unit: PERCENT.

- [C4 F1 Score](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline.md?metric=C4%20F1%20Score>): Higher is better; unit: PERCENT.

- [Macro F1 Score](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline.md?metric=Macro%20F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/e-commerce-search-relevance-classification-on-gold-benchmark-offline-offline.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | C1 F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| DyKnow-RAG | 49.48 | Not recorded | 68fa7c201e209131cea8c8ce |
| DyKnow-RAG | 47.96 | Not recorded | 68fa7c201e209131cea8c8ce |
| RAG GRPO | 47.54 | Not recorded | 68fa7c201e209131cea8c8ce |
| RAG DPO | 45.66 | Not recorded | 68fa7c201e209131cea8c8ce |
| SFT-only | 41.97 | Not recorded | 68fa7c201e209131cea8c8ce |
| RAG SFT | 40.47 | Not recorded | 68fa7c201e209131cea8c8ce |

### DyKnow-RAG

C1 F1 Score: 49.48. Result ID: 69d4b25747f34ce924bc21e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

Recorded evaluation configuration: {"Initialization":"SFT"}. This record does not assert independent reproduction.

### DyKnow-RAG

C1 F1 Score: 47.96. Result ID: 69d4b25747f34ce924bc21e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

Recorded evaluation configuration: {"Initialization":"DPO"}. This record does not assert independent reproduction.

### RAG GRPO

C1 F1 Score: 47.54. Result ID: 69d4b25747f34ce924bc21e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RAG DPO

C1 F1 Score: 45.66. Result ID: 69d4b25747f34ce924bc21e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea6105d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SFT-only

C1 F1 Score: 41.97. Result ID: 69d4b25747f34ce924bc21e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RAG SFT

C1 F1 Score: 40.47. Result ID: 69d4b25747f34ce924bc21e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c201e209131cea8c8ce.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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