Command Palette

Search for a command to run...

DeepSeek V3.2 (Non-reasoning)

DeepSeek

MIT

Analysis of DeepSeek's DeepSeek V3.2 (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date
Dec 01, 2025
Window
128k

PricingPer 1M tokens

Input
$0.5
Output
$1.6
Blended 3:1
$0.775

Capabilities

Input
Output
Reasoning tokens

Benchmarks

Intelligence
●●○○○
Math
●●●○○
Coding
●●○○○
MMLU Pro
83.7%
GPQA
75.1%
HLE
10.5%
SciCode
38.7%
AIME
59.0%
LiveCodeBench
59.3%

Analysis of DeepSeek's DeepSeek V3.2 (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.