← All Comparisons

GPT-5 vs Claude Haiku 4.5

A detailed comparison of GPT-5 (OpenAI) and Claude Haiku 4.5 (Anthropic) across pricing, performance, and features.

Pricing Comparison

MetricGPT-5Claude Haiku 4.5Difference
Input / 1M tokens$1.25$0.80-36%
Output / 1M tokens$10.00$4.00-60%
Context window128K200K
Max output16.384K8.192K

Benchmark Comparison

BenchmarkGPT-5Claude Haiku 4.5
MMLU-Pro88.5%69.4%
HumanEval95%88.1%
GPQA73.5%

Capabilities

CapabilityGPT-5Claude Haiku 4.5
audio
code
reasoning
text
tool-use
vision

GPT-5 Strengths

  • Strong all-around performance
  • Good price for flagship tier
  • Multimodal including audio

GPT-5 Weaknesses

  • 128K context vs 200K+ for newer models
  • Codex variants better for pure coding

Claude Haiku 4.5 Strengths

  • Very fast responses
  • Cheapest Anthropic option
  • Good for classification and extraction

Claude Haiku 4.5 Weaknesses

  • Weakest reasoning in the Claude family
  • Can struggle with nuanced instructions

Quick Verdict

Best value: Claude Haiku 4.5 is the more affordable option at $0.8/$4 per 1M tokens.

Higher benchmarks: GPT-5 scores higher on average across available benchmarks (85.7% avg).

Larger context: Claude Haiku 4.5 supports 200K tokens.

Choose Claude Haiku 4.5 if cost matters most. Choose GPT-5 if you need the best possible quality for complex tasks.

More Comparisons