Skip to content
← Leaderboard

Jev

Closed
TypeSafe AI
Proprietary
text
JevReleased 1mo ago
Decision Index
57.9
/ 100 · single-choice tasks, not comparable with chat models
Context
—
Output limit
—
Input price
—
Output price
—

Benchmarks

decision

Decision IndexSome risk
/100

Overall score of a decision model on a suite of single-choice tasks (knowledge, language, retrieval, tool use, arts), using the suite's own weighting rather than a plain average of the five categories. Measures how often the model picks the right answer from a fixed set; not comparable with chat-model benchmarks.

Decision Index · KnowledgeSome risk
/100

Knowledge category of the Decision Index.

Decision Index · LanguageSome risk
/100

Language category of the Decision Index.

Decision Index · RetrievalSome risk
/100

Retrieval category of the Decision Index.

Decision Index · ToolsSome risk
/100

Tool-use category of the Decision Index.

Decision Index · ArtsSome risk
/100

Arts category of the Decision Index.

Reliability monitor

Loading drift signal…

Hosted endpoints

No third-party hosts tracked for this model — available only from its primary provider.

Compare with...