Claude Sonnet 4 vs Claude Sonnet 4.6
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Claude Sonnet 4.6 by Anthropic wins on 10 of 18 benchmarks against Claude Sonnet 4 by Anthropic, which leads on 3. 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 4.6 scores 1395 on Chatbot Arena ELO compared to Claude Sonnet 4's 1365, while Claude Sonnet 4.6 scores 84.0% on MMLU-Pro compared to Claude Sonnet 4's 81.0%, while Claude Sonnet 4.6 scores 89.0% on IFEval compared to Claude Sonnet 4's 87.0%.
Coding: In coding, Claude Sonnet 4.6 scores 91.0% on HumanEval+ compared to Claude Sonnet 4's 88.0%, while Claude Sonnet 4.6 scores 79.6% on SWE-bench Verified compared to Claude Sonnet 4's 72.7%, while Claude Sonnet 4.6 scores 65.0% on LiveCodeBench compared to Claude Sonnet 4's 58.0%, while both score 70.3% on BFCL, while Claude Sonnet 4.6 scores 63 on AA Coding Index compared to Claude Sonnet 4's 37.6.
Math: In math, Claude Sonnet 4.6 scores 88.0% on MATH compared to Claude Sonnet 4's 85.0%, while Claude Sonnet 4.6 scores 96.0% on GSM8K compared to Claude Sonnet 4's 94.5%.
Reasoning: In reasoning, Claude Sonnet 4 scores 75.4% on GPQA Diamond compared to Claude Sonnet 4.6's 74.1%, while Claude Sonnet 4.6 scores 48.0% on ARC-AGI compared to Claude Sonnet 4's 42.0%.
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 4.6 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 4.6's 57 tok/s, and the time to first token is 400 ms for Claude Sonnet 4 versus 790 ms for Claude Sonnet 4.6. 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 4.6 is the stronger choice.
View Individual Model Pages
Claude Sonnet 4 vs Claude Sonnet 4.6 — FAQ
Which is better, Claude Sonnet 4 or Claude Sonnet 4.6?
Claude Sonnet 4.6 wins on more benchmarks overall (10 vs 3). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude Sonnet 4 compare to Claude Sonnet 4.6 for coding?
Claude Sonnet 4.6 is better for coding, scoring 79.6% 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 4.6?
Both models are priced the same at $3.0/1M input tokens. Claude Sonnet 4 output costs $15.0/1M and Claude Sonnet 4.6 output costs $15.0/1M.
Which is faster, Claude Sonnet 4 or Claude Sonnet 4.6?
Claude Sonnet 4 is faster, generating output at 75 tok/s compared to 57 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Claude Sonnet 4 vs Claude Sonnet 4.6 comparison cover?
This comparison covers 18 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, IFEval, MATH, GPQA Diamond, SWE-bench Verified, Output Speed, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.