Gemini 3 Pro Preview (high)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Gemini 3 Pro Preview high by Google: Text model; TTFT 33.225s, 131.1 tok/s.

Input Modality

Output Modality

Inference Speed

131.059 tokens/s

Latest Release Date

11/18/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Gemini 3 Pro Preview (high)

Release date

11/18/2025

Performance

131.059 tokens/s

model_creator.name

Google

AA Evaluation Scores

AA Intelligence Index

48.4

AA Coding Index

46.5

AA Math Index

95.7

MMLU Pro

0.898

GPQA

0.908

HLE

0.372

LiveCodeBench

0.917

SciCode

0.561

Math-500

AIME

AIME 2025

0.957

IFBench

0.704

LCR

0.707

TerminalBench Hard

0.417

TAU2

0.871

Output Speed (tokens/s)

131.059 tok/s

TTFT (s)

33.225s

First Answer Token (s)

33.225s

Google

◎

Gemini 3 Pro Preview (high)

$2.00/M$12.00/M

Gemini 3 Pro Preview high by Google: Text model; TTFT 33.225s, 131.1 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0