# Text Ranking on BEIR Touche (out-domain)

Source: [Text Ranking on BEIR Touche (out-domain)](<https://www.sota2.com/research/sota/text-ranking-on-beir-touche-out-domain>)

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

Data updated: 2026-02-26T06:11:08.698Z

Evaluation of Text Ranking performance using nDCG@10 on the out-of-domain subset of the BEIR Touche benchmark.

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 | Text Ranking |
| Dataset (including any stated split) | BEIR Touche (out-domain) |
| Metric | nDCG@10 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [nDCG@10](<https://www.sota2.com/research/sota/text-ranking-on-beir-touche-out-domain.md?metric=nDCG%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | nDCG@10 | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4 | 38.6 | Not recorded | 68fa73651e209131cea5c2ea |
| UL2-20B | 37.9 | Not recorded | 68fa73651e209131cea5c2ea |
| ChatGPT | 36.2 | Not recorded | 68fa73651e209131cea5c2ea |
| TSARankLLM | 32 | Not recorded | 68fa73651e209131cea5c2ea |

### GPT-4

nDCG@10: 38.6. Result ID: 6992d8ba3a6c31484911e63f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Ranking Strategy":"Listwise"}. This record does not assert independent reproduction.

### UL2-20B

nDCG@10: 37.9. Result ID: 6992d8ba3a6c31484911e63d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2ea.md>)

Recorded evaluation configuration: {"Ranking Strategy":"Pairwise"}. This record does not assert independent reproduction.

### ChatGPT

nDCG@10: 36.2. Result ID: 6992d8ba3a6c31484911e63e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2ea.md>)

Recorded evaluation configuration: {"Ranking Strategy":"Listwise"}. This record does not assert independent reproduction.

### TSARankLLM

nDCG@10: 32. Result ID: 6992d8ba3a6c31484911e640.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2ea.md>)

[Implementation](<https://github.com/Alibaba-NLP/RankingGPT>)

Recorded evaluation configuration: {"Base Model":"LLaMA-7B"}. This record does not assert independent reproduction.

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