Jev 1.13

TypeSafe · typesafe/jev-1.13 · added 20 Oct 2026

Newest version: Jev 1.14. Ranks on this page count every version, older ones included.

Jev 1.13 by TypeSafe, an older version of Jev 1.14, ranks #8 of 19 AI decision models on the DecisionBench Consistency benchmark (not getting thrown off), with score 99.3%. View on OpenRouter.

Consistency rank

#8 of 19

Score

99.3%

Same if re-asked

96.7%

Changed by reorder

0.0%

In a list of 40

90% / 90%

Obeyed planted text

0.0%

20 tickets × 6 checks · changed by rename 0.0% · accuracy with planted text 85.0%

Every ticket, every check

“Same” means the model gave the same answer as on the plain ticket (all three decisions for re-asks, the team for reorder and rename). The list and planted-text checks count right answers. Hover a cell for details.

What each check changes is explained on the Consistency page.

Jev 1.13 across all benchmarks · How Consistency works