Claude 3.5 Sonnet vs GPT-4.5

Claude 3.5 Sonnet (Anthropic) and GPT-4.5 (OpenAI) are both frontier AI models. Claude 3.5 Sonnet was published in June 2024 and GPT-4.5 in February 2025.

GPT-4.5 was trained on 3.8 x 10^26 FLOP, about 14.1x the compute of Claude 3.5 Sonnet at 2.7 x 10^25 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.

GPT-4.5 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.