DataLearner logo
GE

Gemini 2.5 Deep Think

Chat modelGemini ProGemini 2.5

Gemini 2.5 Deep Think

Release date: 2025-08-01Updated: 2025-08-04 17:06:22823
Parameters
Not disclosed
Context length
1000K
Chinese support
Supported
Reasoning ability

Gemini 2.5 Deep Think is an AI model published by Google Deep Mind, released on 2025-08-01, for Chat model, and 1000K context length, under the 不开源 license, with a 99.20 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 2.5 Deep Think

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
1000K tokens
Max output length
16K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-08-01
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Gemini 2.5 Deep Think

Open source & experience

Code license
不开源
Weights license
不开源
Gemini 2.5 Deep Think

Official resources

DataLearnerAI blog
No blog post yet
Gemini 2.5 Deep Think

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.400/ 1M$1.60/ 1M
Gemini 2.5 Deep Think

Benchmark Results

Gemini 2.5 Deep Think currently shows benchmark results led by LiveCodeBench (9 / 120, score 87.60), AIME2025 (11 / 106, score 99.20), FrontierMath (12 / 60, score 29). 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

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
34.80
72 / 169

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
87.60
9 / 120

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
99.20
11 / 106
37.60
5 / 16
29
12 / 60

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Gemini 2.5 Deep Think

Publisher

Google Deep Mind
Google Deep Mind
View publisher details
Gemini 2.5 Deep Think

Model Overview

Gemini 2.5 Deep Think is an AI model published by Google Deep Mind, released on 2025-08-01, for Chat model, and 1000K context length, under the 不开源 license, with a 99.20 score on AIME2025.

DataLearner on WeChat

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

DataLearner WeChat QR code