← Back to case files
CASE FILE / Model & agent routing
Had jev, claude haiku 4
Had jev, claude haiku 4.5, and gemini 3.5 flash-lite play tetris. Same 200 pieces, same legal moves, real time. Jev: 9200 pts, 75 lines, 300ms/move, 0 errors Claude: 8900 pts, 72 lines, 1.52s/move, 0 errors, $0.48 Gemini: 9000 pts, 75 lines, 1.13s/move, 0 errors, $0.02 Jev wins on score and is doing it 4-5x faster per move than either LLM, for basically free. That gap isn't the model being smarter, it is the model doing less work per decision
● ● ●CASE FILEGUIDE
Ashutosh Mathore · @ashutoshftw
Original post
Had jev, claude haiku 4.5, and gemini 3.5 flash-lite play tetris. Same 200 pieces, same legal moves, real time. Jev: 9200 pts, 75 lines, 300ms/move, 0 errors Claude: 8900 pts, 72 lines, 1.52s/move, 0 errors, $0.48 Gemini: 9000 pts, 75 lines, 1.13s/move, 0 errors, $0.02 Jev wins on score and is doing it 4-5x faster per move than either LLM, for basically free. That gap isn't the model being smarter, it is the model doing less work per decision
Views 20,157Likes 122Reposts 7
Chinese translation
让Jev、Claude俳句4.5和Gemini 3.5 Flash精简版玩俄罗斯方块。同样的200件作品，同样的法律动作，实时。 Jev：9200分，75线，300 ms/移动，0错误 克劳德：8900分，72行，1.52秒/移动，0错误，0.48美元 双子座：9000分，75线，1.13秒/移动，0错误，0.02美元 Jev凭借得分获胜，每一步的速度比任何LLM快4- 5倍，基本上是免费的。这种差距不是模型更聪明，而是模型每次决策所做的工作更少
What this case shows
- Let JEV choose the model or tool first
- Auto-route on high confidence, escalate otherwise
- This is the most common production pattern