← All updates Databricks Update One-Pager Navy version
databricks Platform · Updated Oct 9, 2026

Use OpenJev as the evaluator for LLM-as-a-judge service policies (Beta)

You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM as a judge service policy.

Beta Open docs ↗release note ↗
What it does

You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM as a judge service policy. OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator. Beta This feature is in Beta.

Why it matters

OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator.

Architecture
Databricks Platform → Platform
In short

You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM as a judge service policy. OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator.

Read the full documentation ↗
Key takeaway
You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM as a judge service policy.
2026-10-09-use-openjev-as-the-evaluator-for-llm-as-a-judge-service-policies-beta Generated by the Databricks Updates Agent · browse all updates