token.app › Compare › GPT-4 Turbo vs Claude Sonnet 5

GPT-4 Turbo vs Claude Sonnet 5

Claude Sonnet 5 leads on 2 of 2 shared benchmarks. Claude Sonnet 5 is 3.8× cheaper per token on a blended 3:1 basis. Claude Sonnet 5 accepts the larger context window (1M).

Head to head
Blended price uses a 3:1 input:output mix
GPT-4 TurboClaude Sonnet 5
ProviderOpenAIAnthropic
Input $/1M$10.00$2.00
Output $/1M$30.00$10.00
Blended $/1M$15.00$4.00
Context window128K1M
Max output4K128K
ReleasedApr 2024Jun 2026
LicenceProprietaryProprietary
GPQA Diamond 46.6% 90.5%
OTIS Mock AIME 6.7% 94.7%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-4 Turbo if…
  • No clear advantage on the data we hold.
Choose Claude Sonnet 5 if…
  • Costs less per token — $4.00 vs $15.00 blended
  • Higher GPQA Diamond (90.5% vs 46.6%)
  • Higher OTIS Mock AIME (94.7% vs 6.7%)
  • Larger context window (1M)
  • Newer model (released Jun 2026)
FAQ
Which is better, GPT-4 Turbo or Claude Sonnet 5?
Across the 2 benchmarks both models have independently-run scores for, GPT-4 Turbo leads on 0 and Claude Sonnet 5 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is GPT-4 Turbo cheaper than Claude Sonnet 5?
Claude Sonnet 5 is cheaper: $4.00 versus $15.00 per million tokens blended at 3:1 input:output. Input alone: $10.00 vs $2.00. Output alone: $30.00 vs $10.00.
What context windows do GPT-4 Turbo and Claude Sonnet 5 have?
GPT-4 Turbo: 128,000 tokens. Claude Sonnet 5: 1,000,000 tokens.
Who makes GPT-4 Turbo and Claude Sonnet 5?
GPT-4 Turbo is made by OpenAI. Claude Sonnet 5 is made by Anthropic.
Related comparisons