Comprehensive side-by-side LLM comparison
GPT-5 nano leads with 37.9% higher average benchmark score. GPT-5 nano offers 128.0K more tokens in context window than Claude 3 Haiku. GPT-5 nano is $1.05 cheaper per million tokens. Overall, GPT-5 nano is the stronger choice for coding tasks.
Anthropic
Claude 3 Haiku was created as the fastest and most affordable model in its intelligence class, processing 21K tokens per second for prompts under 32K tokens. Built for enterprise workloads requiring quick analysis of large datasets, it combines state-of-the-art vision capabilities with strong performance on industry benchmarks while prioritizing speed, affordability, and enterprise-grade security.
OpenAI
GPT-5 Nano was developed as the most compact variant in the GPT-5 family, designed for deployment in resource-constrained environments and edge computing scenarios. Built to bring next-generation AI capabilities to devices and applications where latency and efficiency are paramount, it distills GPT-5 innovations into a minimal footprint.
1 year newer

Claude 3 Haiku
Anthropic
2024-03-13

GPT-5 nano
OpenAI
2025-08-07
Cost per million tokens (USD)

Claude 3 Haiku

GPT-5 nano
Context window and performance specifications
Average performance across 1 common benchmarks

Claude 3 Haiku

GPT-5 nano
GPT-5 nano
2024-05-30
Available providers and their performance metrics

Claude 3 Haiku
Anthropic
Bedrock

Claude 3 Haiku

GPT-5 nano

Claude 3 Haiku

GPT-5 nano

GPT-5 nano
OpenAI
ZeroEval