# Retrieval-Augmented Generation on RAG Evaluation Dataset 99 queries (test)

Source: [Retrieval-Augmented Generation on RAG Evaluation Dataset 99 queries (test)](<https://www.sota2.com/research/sota/retrieval-augmented-generation-on-rag-evaluation-dataset-99-queries-test>)

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

Data updated: 2026-03-27T13:14:10.293Z

Evaluation of Retrieval-Augmented Generation performance using 99 test queries, focusing on retrieval completeness and answer correctness.

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 | Retrieval-Augmented Generation |
| Dataset (including any stated split) | RAG Evaluation Dataset 99 queries (test) |
| Metric | Retrieval Completeness |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Retrieval Completeness](<https://www.sota2.com/research/sota/retrieval-augmented-generation-on-rag-evaluation-dataset-99-queries-test.md?metric=Retrieval%20Completeness>): Higher is better; unit: PERCENT.

- [Answer Correctness](<https://www.sota2.com/research/sota/retrieval-augmented-generation-on-rag-evaluation-dataset-99-queries-test.md?metric=Answer%20Correctness>): Higher is better; unit: PERCENT.

- [Mean Score](<https://www.sota2.com/research/sota/retrieval-augmented-generation-on-rag-evaluation-dataset-99-queries-test.md?metric=Mean%20Score>): Higher is better; unit: PERCENT.

- [Answered Queries Count](<https://www.sota2.com/research/sota/retrieval-augmented-generation-on-rag-evaluation-dataset-99-queries-test.md?metric=Answered%20Queries%20Count>): Higher is better; unit: SCALAR.

- [Total Queries](<https://www.sota2.com/research/sota/retrieval-augmented-generation-on-rag-evaluation-dataset-99-queries-test.md?metric=Total%20Queries>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Retrieval Completeness | Result date | Report paper |
| --- | --- | --- | --- |
| Adaptive Chunking | 67.68 | Not recorded | 69c60f2d0636e5bf4afc860d |
| page (raw) | 59.09 | Not recorded | 69c60f2d0636e5bf4afc860d |
| LC recursive (default) | 58.08 | Not recorded | 69c60f2d0636e5bf4afc860d |

### Adaptive Chunking

Retrieval Completeness: 67.68. Result ID: 69c6828f47f34ce924b09335.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f2d0636e5bf4afc860d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60f2d0636e5bf4afc860d.md>)

Recorded evaluation configuration: {"LLM Judge":"GPT-4.1","Temperature":"0","Search Pipeline":"fixed hybrid search pipeline"}. This record does not assert independent reproduction.

### page (raw)

Retrieval Completeness: 59.09. Result ID: 69c6828f47f34ce924b09337.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f2d0636e5bf4afc860d.md>)

Recorded evaluation configuration: {"LLM Judge":"GPT-4.1","Temperature":"0","Search Pipeline":"fixed hybrid search pipeline"}. This record does not assert independent reproduction.

### LC recursive (default)

Retrieval Completeness: 58.08. Result ID: 69c6828f47f34ce924b09336.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f2d0636e5bf4afc860d.md>)

Recorded evaluation configuration: {"LLM Judge":"GPT-4.1","Temperature":"0","Search Pipeline":"fixed hybrid search pipeline","Source":"LangChain"}. This record does not assert independent reproduction.

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