# AWS evaluates Grok 4.7 agents on long-horizon tasks

> An October 13 AWS technical post tested a tool-using agent with Grok 4.7 on Bedrock across three synthetic search tasks. Each task had one answer verified by brute force; six runs at each of four reasoning levels made 72 runs in total.

- Canonical URL: https://newsverum.com/en/news/aws-grok47-long-horizon-agents-bedrock-oct2026
- Publisher: Newsverum
- Section: Technology
- Published: 2026-10-15T21:30:20+00:00
- Updated: 2026-10-15T21:30:20+00:00
- Source review period: 2026-10-13
- Other editions: [Türkçe](https://newsverum.com/tr/news/aws-grok47-long-horizon-agents-bedrock-oct2026.md), [العربية](https://newsverum.com/ar/news/aws-grok47-long-horizon-agents-bedrock-oct2026.md), [Français](https://newsverum.com/fr/news/aws-grok47-long-horizon-agents-bedrock-oct2026.md), [Español](https://newsverum.com/es/news/aws-grok47-long-horizon-agents-bedrock-oct2026.md), [Deutsch](https://newsverum.com/de/news/aws-grok47-long-horizon-agents-bedrock-oct2026.md), [Português](https://newsverum.com/pt/news/aws-grok47-long-horizon-agents-bedrock-oct2026.md)

*The source does not state the event date; the period shown is the source review period.*

The agent answered 67 of 72 runs correctly: 18/18 at xhigh and 15/18 at low. Low used about one-eighth as many output tokens as xhigh. AWS calls results from this small synthetic test indicative and says it did not measure real-world latency or failures. Bedrock availability was announced on September 28; this is an evaluation report, not a new access launch.

## Data

### AWS evaluates Grok 4.7 agents on long-horizon tasks

AWS evaluates Grok 4.7 agents on long-horizon tasks

Methodology: A source-reported technical account; not an independent experiment.

| date | label | description | status |
|---|---|---|---|
| 2026-10-13 | Source publication date | An October 13 AWS technical post tested a tool-using agent with Grok 4.7 on Bedrock across three synthetic search tasks. Each task had one answer verified by brute force; six runs at each of four reasoning levels made 72 runs in total. | occurred |

Sources: <https://aws.amazon.com/blogs/machine-learning/build-long-horizon-agents-with-grok-4-7-on-amazon-bedrock/> · Download data: [JSON](https://newsverum.com/api/v1/articles/aws-grok47-long-horizon-agents-bedrock-oct2026/data/reported-event?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/aws-grok47-long-horizon-agents-bedrock-oct2026/data/reported-event?lang=en&format=csv)

## Sources

- [AWS](<https://aws.amazon.com/blogs/machine-learning/build-long-horizon-agents-with-grok-4-7-on-amazon-bedrock/>) (Source checked: 2026-10-15; Published: 2026-10-13)

---

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