Gemini 2.0 Flash
Highly efficient workhorse model with low latency and enhanced performance.
Gemini 2.0 Flash is a specific Gemini API model release with model code `gemini-2.0-flash`. The official model page lists multimodal inputs—audio, images, video, and text—with text output, a 1,048,576-token input limit, and an 8,192-token output limit; it also notes the model was shut down on June 1, 2026.
Pricing
Model profile · Current snapshot
Output TPS
0
TTFT (s)
0
Model Intelligence
Context window
1,048,576 tokens
Arena ranking
12
Benchmarkable
Yes
Model level
release
Intelligence Index
12.2
Math Index
21.7
MMLU Pro
0.78
GPQA
0.62
HLE
0.04
LiveCodeBench
0.33
SciCode
0.33
MATH-500
0.93
AIME
0.33
AIME 2025
0.22
IFBench
0.4
LCR
0.32
TerminalBench Hard
0.04
TAU2
0.3
Recent stories
0 linked stories
No linked stories yet.