Gemini 3 Flash Preview (Reasoning)

Google

ReasoningVision ModelProprietary

Analysis of Google's Gemini 3 Flash Preview (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 17, 2025
Knowledge Cutoff: Jan 01, 2025
Window: 1M

PricingPer 1M tokens

Input: $0.5
Output: $3
Blended 3:1: $1.125

Capabilities

Speed: 181 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 7.92 ms
500 token response: 10.69 s

Benchmarks

Reasoning: ●●○○○
Math: ●●●●●
Coding: ●●○○○
MMLU Pro: 89.0%
GPQA: 89.8%
HLE: 34.7%
SciCode: 50.6%
AIME: 97.0%
LiveCodeBench: 90.8%

Analysis of Google's Gemini 3 Flash Preview (Reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.