The disconnection between pelican quality and overall model quality is interesting. I initially assumed that since pre-training is when a model gets its general skill that it happened around when RL started to really differentiate models. That is higher quality pre-trains result in higher quality pelicans, but RL is unlikely to touch pelican quality. However the fact that GLM 5.2 beats GPT 5.6 and Claude Fable puts a damper on that idea.
My only guess is that GLM 5.2 was specifically RLed for SVG generation and that resulted in superior performance.
My only guess is that GLM 5.2 was specifically RLed for SVG generation and that resulted in superior performance.