An experiment comparing play performance by giving the same
Compared Jev and Claude Haiku 4.5 on the same Tetris board and candidate moves to measure play performance.
The original post, translated
An experiment comparing play performance by giving the same Tetris board and candidate moves to the specialized decision model "Jev" and the general-purpose language model "Claude Haiku 4.5" I tried it too Certainly Jev's speed and cost are appealing, but if you get creative with the data you pass in, Haiku is a bit smarter than in the original tweet ※ This is Jev via Vercel AI Gateway
Show the original post in its source language ▾
同じテトリス盤面と候補手を、特化型判断モデル「Jev」と汎用言語モデル「Claude Haiku 4.5」に渡し、プレイ性能を比較する実験 私も試してみました 確かにJevの速度・コストは魅力ですが、渡すデータ工夫すれば元ツイートよりもうちょいHaikuは賢いっすね ※ Vercel AI Gateway 経由のJevです
The post above is a machine translation from ja; the untranslated text is in the fold-out.
Engagement when collected
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 general Jev builds. 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. Browse the full case library for the work it sits next to.
Keep browsing: all 1173 Jev cases · more from @xhackjp1 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post