Claude Sonnet 4 vs Claude Sonnet 4.5
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Claude Sonnet 4.5 by Anthropic wins on 14 of 20 benchmarks against Claude Sonnet 4 by Anthropic, which leads on 2. 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, Claude Sonnet 4.5 scores 1380 on Chatbot Arena ELO compared to Claude Sonnet 4's 1365, while Claude Sonnet 4.5 scores 83.0% on MMLU-Pro compared to Claude Sonnet 4's 81.0%, while Claude Sonnet 4.5 scores 88.0% on IFEval compared to Claude Sonnet 4's 87.0%.
Coding: In coding, Claude Sonnet 4.5 scores 90.0% on HumanEval+ compared to Claude Sonnet 4's 88.0%, while Claude Sonnet 4.5 scores 77.2% on SWE-bench Verified compared to Claude Sonnet 4's 72.7%, while Claude Sonnet 4.5 scores 62.0% on LiveCodeBench compared to Claude Sonnet 4's 58.0%, while Claude Sonnet 4.5 scores 52.1 on AA Coding Index compared to Claude Sonnet 4's 37.6, while Claude Sonnet 4.5 scores 1184 on Design Arena ELO compared to Claude Sonnet 4's 1145, while Claude Sonnet 4.5 scores 1202 on Website Arena ELO compared to Claude Sonnet 4's 1151.
Math: In math, Claude Sonnet 4.5 scores 87.0% on MATH compared to Claude Sonnet 4's 85.0%, while Claude Sonnet 4.5 scores 95.5% on GSM8K compared to Claude Sonnet 4's 94.5%.
Reasoning: In reasoning, Claude Sonnet 4.5 scores 82.5% on GPQA Diamond compared to Claude Sonnet 4's 76.7%, while Claude Sonnet 4.5 scores 45.0% on ARC-AGI compared to Claude Sonnet 4's 42.0%, while Claude Sonnet 4.5 scores 73.0% on τ²-Bench Airline compared to Claude Sonnet 4's 68.0%.
Context: In context, both score 1.0M on Context Length.
Pricing Comparison
Claude Sonnet 4 costs $3.0/1M input tokens and $15.0/1M output tokens, while Claude Sonnet 4.5 costs $3.0/1M input and $15.0/1M output. Both models are priced identically for input tokens.
Speed Comparison
Claude Sonnet 4 generates output at 75 tok/s compared to Claude Sonnet 4.5's 67 tok/s, and the time to first token is 400 ms for Claude Sonnet 4 versus 1170 ms for Claude Sonnet 4.5. Claude Sonnet 4 delivers faster throughput.
Verdict
For developers prioritizing speed, Claude Sonnet 4 has the edge. For those who value coding and general intelligence and math, Claude Sonnet 4.5 is the stronger choice.
View Individual Model Pages
Claude Sonnet 4 vs Claude Sonnet 4.5 — FAQ
Which is better, Claude Sonnet 4 or Claude Sonnet 4.5?
Claude Sonnet 4.5 wins on more benchmarks overall (14 vs 2). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude Sonnet 4 compare to Claude Sonnet 4.5 for coding?
Claude Sonnet 4.5 is better for coding, scoring 77.2% on SWE-bench Verified compared to 72.7%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Claude Sonnet 4 cheaper than Claude Sonnet 4.5?
Both models are priced the same at $3.0/1M input tokens. Claude Sonnet 4 output costs $15.0/1M and Claude Sonnet 4.5 output costs $15.0/1M.
Which is faster, Claude Sonnet 4 or Claude Sonnet 4.5?
Claude Sonnet 4 is faster, generating output at 75 tok/s compared to 67 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Claude Sonnet 4 vs Claude Sonnet 4.5 comparison cover?
This comparison covers 20 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, IFEval, MATH, SWE-bench Verified, GPQA Diamond, Output Speed, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.