Claude 3.5 Sonnet vs Grok-2

Claude 3.5 Sonnet (Anthropic) and Grok-2 (xAI) are both frontier AI models. Claude 3.5 Sonnet was published in June 2024 and Grok-2 in August 2024.

Grok-2 was trained on 3×10²⁵ FLOP, essentially the same compute as Claude 3.5 Sonnet at 2.7×10²⁵ 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.