DeepSeek V3.2 Speciale vs Gemini 3 Flash Preview (Reasoning)

Comparing 2 AI models · 5 benchmarks · DeepSeek, Google

Most Affordable
DeepSeek logo
DeepSeek V3.2 Speciale
$0.40/1M
Highest Intelligence
Google logo
Gemini 3 Flash Preview (Reasoning)
89.8% GPQA
Best for Coding
Google logo
Gemini 3 Flash Preview (Reasoning)
41.0 Coding Index
Price Difference
1.3x
input cost range

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Benchmark Winners

5 tests
DeepSeek logo

DeepSeek V3.2 Speciale

0

No clear wins

Google logo

Gemini 3 Flash Preview (Reasoning)

5
  • GPQA
  • MMLU Pro
  • HLE
  • LiveCodeBench
  • AIME 2025
Metric
DeepSeek logo DeepSeek V3.2 Speciale
DeepSeek
Google logo Gemini 3 Flash Preview (Reasoning)
Google
Pricing
Per 1M tokens
Input Cost $0.40/1M $0.50/1M
Output Cost $0.50/1M $3.00/1M
Blended Cost 3:1 input/output ratio
$0.43/1M $1.13/1M
Specifications
Organization Model creator
DeepSeek Google
Release Date Launch date
Dec 1, 2025 Dec 17, 2025
Performance & Speed
Throughput Output speed
217.7 tok/s
Time to First Token (TTFT) Initial response delay