Open Models Almanac
Methodsevaluationjudge

general family · filed under evaluation

LLM-as-a-Judge

An LLM evaluates or scores outputs; the supplied evidence does not establish a more specific shared judging procedure.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See judge for the methods filed beside it.

Also called LLM-based judgement for anti-cheating, LLM-based judgement.

sources
2
models
2
labs adopt it
2
strongest
used

Documented in

MiniMax
Z.ai (Zhipu AI)

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2

GLM-5.3

Z.ai (Zhipu AI)adopted1 source

To prevent hacking, we use rule-based and a LLM-based judgement to prevent malicious behaviors (e.g., unauthorized pip or curl operations).

usedunclearin GLM-5.3Z.ai

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

↑