AILeaderboard.live
Compare

See tradeoffs side by side.

Compare up to four API models by cost, context, benchmark quality, and official links.

Cohere
Command A
Cohere’s enterprise-oriented generation model tuned for agentic workflows and RAG.
Fastestfull
DetailOfficial
OpenAI
GPT-4.1
Flagship general-purpose model tuned for production-grade reasoning and tool use.
Smartestfull
DetailOfficial
Anthropic
Claude Sonnet 4
Balanced Claude model optimized for production coding and long-context tasks.
Codingfull
DetailOfficial
Direct comparison
Winners are highlighted row by row so cost, speed, and context tradeoffs are visible immediately.
MetricCommand AGPT-4.1Claude Sonnet 4
ProviderCohereOpenAIAnthropic
Input / 1M$2.5$2$3
Output / 1M$10$8$15
Context window128K1M200K
Latency1010 ms1400 ms1200 ms
Intelligence849593
Coding789497
Best value score32.772.043.3
Coveragefullfullfull