Claude Sonnet 4.5 vs Gemini 2.5 Flash Preview 05-20 (thinking)
Compare Claude Sonnet 4.5 by Anthropic against Gemini 2.5 Flash Preview 05-20 (thinking) by Google AI, context windows of 200K vs 1.0M, tested across 12 shared challenges.
Our Verdict
Claude Sonnet 4.5
Gemini 2.5 Flash Preview 05-20 (thinking)Runner-up
No community votes yet. On paper, Claude Sonnet 4.5 has the edge — bigger model tier, newer.
Gemini 2.5 Flash Preview 05-20 (thinking) is 4.3x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Claude Sonnet 4.5
Input
$3.00
Output
$15.00
Gemini 2.5 Flash Preview 05-20 (thinking)
Input
$0.15
20× cheaper
Output
$3.50
4.3× cheaper
Gemini 2.5 Flash Preview 05-20 (thinking) is cheaper on both — 20× input, 4.3× output
Writing DNA
Style Comparison
Similarity
52%
Claude Sonnet 4.5 uses 47.9x more hedging
Claude Sonnet 4.5
Gemini 2.5 Flash Preview 05-20 (thinking)
64%Vocabulary70%
94wSentence Length11w
0.48Hedging0.00
4.9Bold4.2
8.0Lists7.3
0.45Emoji0.00
1.91Headings0.00
0.07Transitions0.00
Based on 20 + 3 text responses
Research
What we learned reading every model
FAQ
