EXAONE 1.0 vs PaLM 2

EXAONE 1.0 (LG) and PaLM 2 (Google) are both frontier AI models. EXAONE 1.0 was published in December 2021 and PaLM 2 in May 2023.

PaLM 2 was trained on 7.3×10²⁴ FLOP, about 4.3x the compute of EXAONE 1.0 at 1.7×10²⁴ FLOP. Training compute is the closest available proxy for how much was invested in a model, though it says nothing on its own about how well that compute was spent.

These two models share no benchmark on which both have been scored, so no direct performance comparison is possible here. The specification table below is a comparison of inputs, not of results.