Gemma 4 31B

Name: Gemma 4 31B（稠密旗舰模型）
Author: DeepMind

Chat modelGemmaGemma 4

Gemma 4 31B（稠密旗舰模型）

Release date: 2026-04-02Updated: 2026-04-07 22:08:18.513Knowledge cutoff: 2025-121,516

Live demoGitHubHugging Face Compare

Parameters

3.1B

Context length

256K

Chinese support

Not supported

Reasoning ability

Gemma 4 31B（稠密旗舰模型） is an AI model published by DeepMind, released on 2026-04-02, for Chat model, with 3.1B parameters, and 256K context length, under the Apache 2.0 license, with a 89.20 score on AIME 2026.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemma 4 31B

Model basics

Reasoning traces

Supported

Thinking modes

Thinking Mode (Default)Standard Mode

Context length

256K tokens

Max output length

32K tokens

Model type

Chat model

Modality (in / out)

Text, Image, Video → Text

Release date

2026-04-02

Model file size

No data

MoE architecture

Total params / Active params

3.1B / N/A

Knowledge cutoff

2025-12

Gemma 4 31B

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/google/gemma-4-31b

Live demo

https://ai.google.dev/gemma

Gemma 4 31B

Official resources

Paper

Gemma 4: Byte for byte, the most capable open models

DataLearnerAI blog

Gemma 4 31B

API details

API speed

No data

No public API pricing yet.

Gemma 4 31B

Benchmark Results

Gemma 4 31B currently shows benchmark results led by MMLU Pro (23 / 126, score 85.20), LiveCodeBench (30 / 120, score 80), GPQA Diamond (54 / 179, score 84.30). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.