DeepSeek V3.2 Speciale vs Gemini 3 Flash Preview (Reasoning)
Comparing 2 AI models · 5 benchmarks · DeepSeek, Google
Most Affordable
De
DeepSeek V3.2 Speciale
$0.40/1M
Highest Intelligence
Go
Gemini 3 Flash Preview (Reasoning)
89.8% GPQA
Best for Coding
Go
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
De
DeepSeek V3.2 Speciale
0
No clear wins
Go
Gemini 3 Flash Preview (Reasoning)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | De DeepSeek V3.2 Speciale | Go Gemini 3 Flash Preview (Reasoning) |
|---|---|---|
| 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 | |
| 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 | — | |