The probability of being output by Jev might be believable.

@keimakawada けーま · Sep 21, 2026 · case #548816 · listed via Jev Hub

Compared Jev and Gemini 3.8 Flash on the same 107 cases for speed, cost, and probability reliability.

The original post, translated

The probability of being output by Jev might be believable. 【TypeSafe】Will LLMs get faster if you narrow down the output? I compared the speed and cost of Gemini 3.8 Flash and Jev on the same 107 cases https:// dev.classmethod.jp/articles/jev-v s-gemini-flash-cross-match/ … #DevelopersIO

Show the original post in its source language ▾

Jevで出される確率は、信じられるものかもしれない【TypeSafe】出力を絞ればLLMも速くなる？ Gemini 3.8 Flash と Jev で同じ107ケースの速度・コストを比較してみた https:// dev.classmethod.jp/articles/jev-v s-gemini-flash-cross-match/ … #DevelopersIO

The post above is a machine translation from ja; the untranslated text is in the fold-out.

Engagement when collected

Likes1

Bookmarks0

Reposts0

Replies0

Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the coding & developer tools page.

🛠️ Coding & developer tools