Claude Sonnet 4.5 vs GPT-5.6 Luna
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
GPT-5.6 Luna by OpenAI wins on 8 of 9 benchmarks against Claude Sonnet 4.5 by Anthropic, which leads on 1. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from our benchmark data.
Category-by-Category Breakdown
General Intelligence: In general intelligence, GPT-5.6 Luna scores 37.5 on AA Intelligence Index compared to Claude Sonnet 4.5's 21.2.
Coding: In coding, GPT-5.6 Luna scores 71.4 on AA Coding Index compared to Claude Sonnet 4.5's 52.1.
Reasoning: In reasoning, GPT-5.6 Luna scores 87.7% on GPQA Diamond compared to Claude Sonnet 4.5's 82.5%, while GPT-5.6 Luna scores 42.7 on AA Agentic Index compared to Claude Sonnet 4.5's 17.5, while Claude Sonnet 4.5 scores 73.0% on τ²-Bench Airline compared to GPT-5.6 Luna's 70.7%.
Context: In context, GPT-5.6 Luna scores 1.1M on Context Length compared to Claude Sonnet 4.5's 1.0M.
Pricing Comparison
Claude Sonnet 4.5 costs $3.0/1M input tokens and $15.0/1M output tokens, while GPT-5.6 Luna costs $0.20/1M input and $1.2/1M output. GPT-5.6 Luna is the more affordable option for API usage.
Verdict
GPT-5.6 Luna leads across the board in affordability, making it the stronger overall choice in this comparison.
View Individual Model Pages
Claude Sonnet 4.5 vs GPT-5.6 Luna — FAQ
Which is better, Claude Sonnet 4.5 or GPT-5.6 Luna?
GPT-5.6 Luna wins on more benchmarks overall (8 vs 1). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude Sonnet 4.5 compare to GPT-5.6 Luna for coding?
SWE-bench Verified data is not available for both models. Check the detailed comparison charts above for other coding-related metrics.
Is Claude Sonnet 4.5 cheaper than GPT-5.6 Luna?
Yes, GPT-5.6 Luna is cheaper. Claude Sonnet 4.5 costs $3.0/1M input and $15.0/1M output tokens. GPT-5.6 Luna costs $0.20/1M input and $1.2/1M output tokens.
Which is faster, Claude Sonnet 4.5 or GPT-5.6 Luna?
Output speed data is not available for both models. Check the speed section of the comparison above for available performance data.
What benchmarks does the Claude Sonnet 4.5 vs GPT-5.6 Luna comparison cover?
This comparison covers 9 benchmarks including GPQA Diamond, Input Cost, Output Cost, Context Length, AA Intelligence Index, AA Coding Index, AA Agentic Index, Cached Input Cost, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.