GPT-4 (Mar 2023) (OpenAI) and Grok-2 (xAI) are both frontier AI models. GPT-4 (Mar 2023) was published in March 2023 and Grok-2 in August 2024.
Grok-2 was trained on 3×10²⁵ FLOP, about 1.4x the compute of GPT-4 (Mar 2023) at 2.1×10²⁵ 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.
Grok-2 wins the single benchmark both were scored on. Benchmark counts are a crude scoreboard — the evaluations differ wildly in what they measure and in how saturated they are — so the per-benchmark table below matters more than the tally.
