DeepSeek R1 vs Gemini 2.5 Pro Preview 06-05
Compare DeepSeek R1 by DeepSeek against Gemini 2.5 Pro Preview 06-05 by Google AI, context windows of 128K vs 1.0M, tested across 43 shared challenges.
Our Verdict
Gemini 2.5 Pro Preview 06-05
DeepSeek R1Runner-up
No community votes yet. On paper, Gemini 2.5 Pro Preview 06-05 has the edge — bigger model tier, newer, bigger context window.
DeepSeek R1 is 4.6x cheaper per token — worth considering if cost matters.
Slight edge
API pricing
Cost per 1M tokens
DeepSeek R1
Input
$0.55
2.3× cheaper
Output
$2.19
4.6× cheaper
Gemini 2.5 Pro Preview 06-05
Input
$1.25
Output
$10.00
DeepSeek R1 is cheaper on both — 2.3× input, 4.6× output
Writing DNA
Style Comparison
Similarity
43%
DeepSeek R1 uses 4.3x more emoji
DeepSeek R1
Gemini 2.5 Pro Preview 06-05
62%Vocabulary51%
15wSentence Length15w
0.52Hedging0.31
8.0Bold4.8
5.7Lists4.1
0.04Emoji0.00
0.62Headings0.98
0.28Transitions0.05
Based on 22 + 20 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
