kimi-k2-0905-preview vs gpt-5.4

Direct benchmark comparison between kimi-k2-0905-preview and gpt-5.4 based on LMArena Elo and latest API pricing.

Direct Technical Comparison

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
kimi-k2-0905-preview	1418	$4e-7	23
gpt-5.4	1464	$0.0000025	42

*These models represent the Pareto Frontier (optimal cost-to-performance).*

Conclusion: For developers looking for higher intelligence, gpt-5.4 currently leads with an Elo of 1464.