Back to explore

Jev dalam benchmark pemrograman state machine

Dorian Smiley membagikan benchmark: Gemini Flash Lite 3.1 memperoleh 75,6% keseluruhan, Jev 72,2% keseluruhan, 100% pada tugas kanonik, dan sekitar 6× lebih cepat; kesalahan terutama pada komposisi baru.

New state machine programming benchmark: Gemini Flash Lite 3.1: 75.6% overall, 66.7% generalization. Jev: 72.2% overall, 61.4% generalization, but 100% on canonical tasks and ~6× faster. Jev’s misses are concentrated in specific novel compositions, not broad task failure. It is

Jev dalam benchmark pemrograman state machine 1
· 1 likesOpen on X