Claude Sonnet 4.6 vs Gemini 2.5 Flash Preview 05-20 (thinking)
Compare Claude Sonnet 4.6 by Anthropic against Gemini 2.5 Flash Preview 05-20 (thinking) by Google AI, context windows of 1.0M vs 1.0M, tested across 11 shared challenges.
Our Verdict
Claude Sonnet 4.6
Gemini 2.5 Flash Preview 05-20 (thinking)Runner-up
No community votes yet. On paper, Claude Sonnet 4.6 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 4.6
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
41%
Claude Sonnet 4.6 uses 52.7x more hedging
Claude Sonnet 4.6
Gemini 2.5 Flash Preview 05-20 (thinking)
56%Vocabulary70%
36wSentence Length11w
0.53Hedging0.00
5.1Bold4.2
3.4Lists7.3
0.19Emoji0.00
2.10Headings0.00
0.02Transitions0.00
Based on 23 + 3 text responses
Research
What we learned reading every model
FAQ
