# Verify Qwen3.8 27B Endpoints

Check that an endpoint selling Qwen3.8 27B really serves it. A test compares the endpoint's answers with answers collected from Alibaba, through OpenRouter pinned to Alibaba.

- **Official Provider:** Alibaba, through OpenRouter pinned to Alibaba
- **Reference Answers:** 400
- **Declared Precision:** not disclosed
- **Official Release:** weights BF16 100.0%
- **Checks:** Identity · Refusals (2 probes)
- **Reference Data Updated:** 2026-10-16

## How Well a Test Works

| Size | Requests | Genuine Confirmed | Wrongly Flagged | Substitutes Caught |
|---|---|---|---|---|
| Standard | 80 | 99.5% | 0.5% | 100.0% |
| Thorough | 160 | 99.5% | 0.5% | 100.0% |

Simulated from the reference answers. A substitute that isn't caught ends inconclusive: it is never confirmed as this model.

## Notes

- No competence check yet: the competence check needs hard tasks collected from the official provider, which this model doesn't have.

## Guides

- [How the Identity Check Works](https://llm-id.sh/docs/identity)
- [Testing an Endpoint](https://llm-id.sh/docs/testing-an-endpoint)
- [Refusal Check](https://llm-id.sh/docs/refusals)
- [Limits](https://llm-id.sh/docs/limits)

Test a Qwen3.8 27B endpoint: https://llm-id.sh/app#new

---

From llm-id.sh: https://llm-id.sh/models/qwen3.8-27b