TPSTokens Per Second

Gemini 3 Flash

Google DeepMind🇺🇸 United States
active

Fast, cost-efficient Gemini 3 workhorse with near-Pro reasoning at a fraction of the cost. 1M context. Rolled out globally in the Gemini app, Search AI Mode, and the API on day one.

Compare with other models →
Context window1049K tokens
Input / 1M tokens$0.5
Output / 1M tokens$3

Version History

gemini-3-flash-launchmajor

Gemini 3 Flash launches. Fast, cost-efficient Gemini 3 workhorse with near-Pro reasoning at a fraction of the cost. 1M context. Rolled out globally in the Gemini app, Search AI Mode, and the API on day one.

Benchmark Scores

Full leaderboard →
99.7%
AIME 2025
1473.0 elo
Arena Elo
81.2%
GPQA
79.7%
LiveCodeBench
88.2%
MMLU-Pro
212.0 tokens_per_sec
Speed (tok/s)
78.0%
SWE-bench Verified