Claude 3.5 Sonnet vs Claude 3 Opus
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Claude 3.5 Sonnet by Anthropic wins on 17 of 20 benchmarks against Claude 3 Opus 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, Claude 3.5 Sonnet scores 1268 on Chatbot Arena ELO compared to Claude 3 Opus's 1240, while Claude 3.5 Sonnet scores 73.0% on MMLU-Pro compared to Claude 3 Opus's 68.0%, while Claude 3.5 Sonnet scores 9.1 on MT-Bench compared to Claude 3 Opus's 8.8, while Claude 3.5 Sonnet scores 86.0% on IFEval compared to Claude 3 Opus's 82.0%, while Claude 3 Opus scores 29.0% on SimpleQA compared to Claude 3.5 Sonnet's 28.9%, while Claude 3.5 Sonnet scores 84.2% on TruthfulQA compared to Claude 3 Opus's 81.0%.
Coding: In coding, Claude 3.5 Sonnet scores 81.7% on HumanEval+ compared to Claude 3 Opus's 78.0%, while Claude 3.5 Sonnet scores 49.0% on SWE-bench Verified compared to Claude 3 Opus's 22.0%, while Claude 3.5 Sonnet scores 38.0% on LiveCodeBench compared to Claude 3 Opus's 32.0%.
Math: In math, Claude 3.5 Sonnet scores 78.3% on MATH compared to Claude 3 Opus's 68.0%, while Claude 3.5 Sonnet scores 91.0% on GSM8K compared to Claude 3 Opus's 88.0%.
Reasoning: In reasoning, both score 59.4% on GPQA Diamond, while Claude 3.5 Sonnet scores 15.0% on ARC-AGI compared to Claude 3 Opus's 8.0%, while Claude 3.5 Sonnet scores 93.1% on BBH compared to Claude 3 Opus's 86.8%, while Claude 3.5 Sonnet scores 91.8% on Winogrande compared to Claude 3 Opus's 90.5%.
Context: In context, both score 200K on Context Length.
Pricing Comparison
Claude 3.5 Sonnet costs $3.0/1M input tokens and $15.0/1M output tokens, while Claude 3 Opus costs $15.0/1M input and $75.0/1M output. Claude 3.5 Sonnet is the more affordable option for API usage.
Speed Comparison
Claude 3.5 Sonnet generates output at 70 tok/s compared to Claude 3 Opus's 25 tok/s, and the time to first token is 400 ms for Claude 3.5 Sonnet versus 800 ms for Claude 3 Opus. Claude 3.5 Sonnet delivers faster throughput.
Verdict
Claude 3.5 Sonnet leads across the board in coding, general intelligence, math, affordability, speed, making it the stronger overall choice in this comparison.
View Individual Model Pages
Claude 3.5 Sonnet vs Claude 3 Opus — FAQ
Which is better, Claude 3.5 Sonnet or Claude 3 Opus?
Claude 3.5 Sonnet wins on more benchmarks overall (17 vs 1). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude 3.5 Sonnet compare to Claude 3 Opus for coding?
Claude 3.5 Sonnet is better for coding, scoring 49.0% on SWE-bench Verified compared to 22.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Claude 3.5 Sonnet cheaper than Claude 3 Opus?
Yes, Claude 3.5 Sonnet is cheaper. Claude 3.5 Sonnet costs $3.0/1M input and $15.0/1M output tokens. Claude 3 Opus costs $15.0/1M input and $75.0/1M output tokens.
Which is faster, Claude 3.5 Sonnet or Claude 3 Opus?
Claude 3.5 Sonnet is faster, generating output at 70 tok/s compared to 25 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Claude 3.5 Sonnet vs Claude 3 Opus comparison cover?
This comparison covers 20 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MT-Bench, IFEval, SimpleQA, MATH, TruthfulQA, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.