Claude Sonnet 3.6 (2022-10-22)
Nothing here. The model returned empty. We stared at it for a while.
Claude Sonnet 3.6 (2022-10-22) vs Claude Sonnet 4.5
Compare Claude Sonnet 3.6 (2022-10-22) and Claude Sonnet 4.5, both from Anthropic, context windows of 200K vs 200K, tested across 43 shared challenges. Updated April 2026.
Which is better, Claude Sonnet 3.6 (2022-10-22) or Claude Sonnet 4.5?
Claude Sonnet 3.6 (2022-10-22) and Claude Sonnet 4.5 are both competitive models. Claude Sonnet 3.6 (2022-10-22) costs $3/M input tokens vs $3/M for Claude Sonnet 4.5. Context windows: 200K vs 200K tokens. Compare their real outputs side by side below.
Key Differences Between Claude Sonnet 3.6 (2022-10-22) and Claude Sonnet 4.5
Claude Sonnet 3.6 (2022-10-22) is made by anthropic while Claude Sonnet 4.5 is from anthropic. Claude Sonnet 3.6 (2022-10-22) has a 200K token context window compared to Claude Sonnet 4.5's 200K. On pricing, Claude Sonnet 3.6 (2022-10-22) costs $3/M input tokens vs $3/M for Claude Sonnet 4.5.
Our Verdict
Claude Sonnet 3.6 (2022-10-22)
Claude Sonnet 4.5
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
Too close to call
Writing DNA
Style Comparison
Similarity
100%
Claude Sonnet 4.5 uses 45.2x more emoji
Claude Sonnet 3.6 (2022-10-22)
Claude Sonnet 4.5
66%Vocabulary64%
74wSentence Length94w
0.72Hedging0.48
0.3Bold4.9
8.9Lists8.0
0.00Emoji0.45
0.06Headings1.91
0.09Transitions0.07
Based on 21 + 20 text responses
vsAsk them anything yourself
279 AI models invented the same fake scientist.
We read every word. 250 models. 2.14 million words. This is what we found.
Free preview13 of 58 slides
FAQ