Paul Iusztin (@pauliusztin_)

While optimizing my coding agent on my custom benchmark, I compared its performance against two models: a 35B vs. a 120B. The winner should be obvious, right? As the 120B model is 3 to 4 times larger (both are MoE). Well... the 35B model had a 95% success rate, while the 120B model had 53%. Auch....