token.app โ€บ Compare โ€บ Claude Sonnet 4.5 vs GPT-5.6 Terra

Claude Sonnet 4.5 vs GPT-5.6 Terra

GPT-5.6 Terra leads on 5 of 5 shared benchmarks. GPT-5.6 Terra is 2.7ร— cheaper per token on a blended 3:1 basis. GPT-5.6 Terra accepts the larger context window (1.1M).

Head to head
Blended price uses a 3:1 input:output mix
Claude Sonnet 4.5GPT-5.6 Terra
ProviderAnthropicOpenAI
Input $/1M$3.00$1.00
Output $/1M$15.00$6.00
Blended $/1M$6.00$2.25
Context window1M1.1M
Max output64K128K
ReleasedSep 2025Jul 2026
LicenceProprietaryProprietary
GPQA Diamond 82.3% 93.3%
FrontierMath T1โ€“3 23.9% 86.0%
FrontierMath T4 2.4% 70.7%
SimpleQA Verified 23.6% 43.1%
OTIS Mock AIME 77.8% 99.7%
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 Claude Sonnet 4.5 ifโ€ฆ
  • No clear advantage on the data we hold.
Choose GPT-5.6 Terra ifโ€ฆ
  • Costs less per token โ€” $2.25 vs $6.00 blended
  • Higher GPQA Diamond (93.3% vs 82.3%)
  • Higher FrontierMath T1โ€“3 (86.0% vs 23.9%)
  • Higher FrontierMath T4 (70.7% vs 2.4%)
  • Higher SimpleQA Verified (43.1% vs 23.6%)
  • Larger context window (1.1M)
  • Newer model (released Jul 2026)
FAQ
Which is better, Claude Sonnet 4.5 or GPT-5.6 Terra?
Across the 5 benchmarks both models have independently-run scores for, Claude Sonnet 4.5 leads on 0 and GPT-5.6 Terra leads on 5. Benchmarks are one input โ€” price and context window are on this page too.
Is Claude Sonnet 4.5 cheaper than GPT-5.6 Terra?
GPT-5.6 Terra is cheaper: $2.25 versus $6.00 per million tokens blended at 3:1 input:output. Input alone: $3.00 vs $1.00. Output alone: $15.00 vs $6.00.
What context windows do Claude Sonnet 4.5 and GPT-5.6 Terra have?
Claude Sonnet 4.5: 1,000,000 tokens. GPT-5.6 Terra: 1,050,000 tokens.
Who makes Claude Sonnet 4.5 and GPT-5.6 Terra?
Claude Sonnet 4.5 is made by Anthropic. GPT-5.6 Terra is made by OpenAI.
Related comparisons