GLM-5.2 vs phi-3-small 7.4B

These two models have no benchmark in common in our data, so there is no apples-to-apples comparison to draw. That absence is itself worth noting.

A higher number is not always a better model. Each score is task performance under a disclosed harness, and some of these benchmarks are saturated or scored under mixed harnesses. Follow any benchmark to its integrity grade before reading a win as decisive.