DataLearner logo
GE

Gemini 3.0 Flash

Chat modelGemini FlashGemini 3.0

Gemini 3.0 Flash

Release date: 2025-12-17Updated: 2026-03-08 21:11:182,538
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
2000K
Chinese support
Supported
Reasoning ability

Gemini 3.0 Flash is an AI model published by Google Deep Mind, released on 2025-12-17, for Chat model, and 2000K context length, under the 不开源 license, with a 99.70 score on AIME2025.

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

Gemini 3.0 Flash

Model basics

Reasoning traces
Supported
Thinking modes
Standard ModeThinking ModeThinking Level · 4KThinking Level · 8KThinking Level · 16KThinking Level · 32KThinking Level · 64K
Context length
2000K tokens
Max output length
64K tokens
Model type
Chat model
Modality (in / out)
Text, Image, Audio, Video → Text
Release date
2025-12-17
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Gemini 3.0 Flash

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Gemini 3.0 Flash

Official resources

Gemini 3.0 Flash

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.500/ 1M$3.00/ 1M
Batch
TypeConditionInputOutput
Text-$0.250/ 1M$1.50/ 1M
Gemini 3.0 Flash

Benchmark Results

Gemini 3.0 Flash currently shows benchmark results led by τ²-Bench (3 / 40, score 90.20), AIME2025 (8 / 106, score 99.70), GPQA Diamond (18 / 180, score 90.40). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

6 evaluations
Benchmark / mode
Score
Rank/total
90.40
18 / 180
LiveBench
Standard Mode
56.35
79 / 115
72.40
26 / 115
43.50
42 / 164
33.70
73 / 164
33.60
27 / 59

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
68.70
7 / 45

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
68.70
63 / 109
49.60
36 / 47

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
99.70
8 / 106
95.20
24 / 106
4.20
40 / 80

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
90.20
3 / 40

AI Agent - Tool Usage

3 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
Standard ModeTools
62
18 / 25
58
18 / 19
47.60
37 / 46

Claw-style Agent Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
85.70
15 / 29
Pinch Bench
Thinking ModeTools
85.20
16 / 37

Compare with other models

Gemini 3.0 Flash

Publisher

Google Deep Mind
Google Deep Mind
View publisher details
Gemini 3.0 Flash

Model Overview

Gemini 3.0 Flash is an AI model published by Google Deep Mind, released on 2025-12-17, for Chat model, and 2000K context length, under the 不开源 license, with a 99.70 score on AIME2025.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code