# AtScale says semantic layer improved all seven AI models tested

> The company reported higher accuracy on business-data questions for seven large language models when used with a semantic layer.

- Canonical URL: https://newsverum.com/en/news/atscale-benchmark-finds-semantic-layer-improves-seven-models
- Publisher: Newsverum
- Section: Technology
- Country: United States
- Published: 2026-10-16T10:36:23+00:00
- Updated: 2026-10-16T10:36:23+00:00
- Event / data period: 2026-10-15
- Other editions: [Türkçe](https://newsverum.com/tr/news/atscale-benchmark-finds-semantic-layer-improves-seven-models.md), [العربية](https://newsverum.com/ar/news/atscale-benchmark-finds-semantic-layer-improves-seven-models.md), [Français](https://newsverum.com/fr/news/atscale-benchmark-finds-semantic-layer-improves-seven-models.md), [Español](https://newsverum.com/es/news/atscale-benchmark-finds-semantic-layer-improves-seven-models.md), [Deutsch](https://newsverum.com/de/news/atscale-benchmark-finds-semantic-layer-improves-seven-models.md), [Português](https://newsverum.com/pt/news/atscale-benchmark-finds-semantic-layer-improves-seven-models.md)

On 15 October, AtScale published results from an evaluation of seven large language models on the BIRD-Interact benchmark. The company said every tested model was more accurate on the 410 business-data questions when paired with a semantic layer, and that an open-weight model reached a level close to frontier models.

The findings are from AtScale’s own experiment; the company labels them preliminary and says the BIRD team has not verified them. The test examines the difference between models querying raw enterprise tables and querying through defined business metrics. It does not establish that every company will see the same gains.

## Data

### AtScale says semantic layer improved all seven AI models tested

AtScale BIRD-Interact evaluation

Methodology: Figures reflect the company’s preliminary evaluation; they are not verified by BIRD and are not independent results.

| date | label | description | status |
|---|---|---|---|
| 2026-10-15 | Evaluation scope | Seven models and 410 business-data questions; improvement with the semantic layer was reported for each model. | occurred |

Sources: <https://www.atscale.com/press/atscale-research-shows-semantic-layers-double-ai-accuracy/> · Download data: [JSON](https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models/data/source-record?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/atscale-benchmark-finds-semantic-layer-improves-seven-models/data/source-record?lang=en&format=csv)

## Sources

- [AtScale](<https://www.atscale.com/press/atscale-research-shows-semantic-layers-double-ai-accuracy/>) (Source checked: 2026-10-16; Published: 2026-10-15)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)