Official-document comparison; not our API run or new game test
Decisions GA: probability, severity and handoffs →
“The same order was charged twice.
TypeSafe AI · Released 2026-10-14
Jev 1.14 Preview
A bounded decision model for text and structured text. jev-preview selects 1.14; stable jev-latest remains on 1.13. Defaults: 64k per request and 32k per question, with optional long context. No comparable result in our three boards; earlier game results concern another version.
Original model explanation ↗No comparable leaderboard score is included yet. Explore the evaluations and examples below.
Evaluations: conditions and results
Published versions and conditions, not a two-version task test
Stable aliases, previews and context limits →
TypeSafe dates Jev 1.14’s availability to October 14, but the stable jev-latest alias still points to 1.13; jev-preview selects 1.14.
Official versions and context limits, not a BitShovel comparison
1.14 preview, 1.13 stable and aliases ↗
Official method, not a general text or coding ranking
System One decisions and probabilities ↗
Published family background, not a dedicated 1.14 test
The Jev family: an email becomes a choice →
An incoming email needs to reach support, billing or partnerships before anyone writes a reply.
TypeSafe AI model evolution
- Jev / System One · 首次公开发布
The first System One model launches; the family-launch date does not establish the later 1.13 release date.
Original release ↗ - Jev 1.14 · 预览可用
jev-preview selects 1.14 while jev-latest stays on stable 1.13; both default to 64k per request and 32k per question, with an optional longer mode.
Original release ↗