GE

Gemini 3.0 Pro (Preview 11-2025)

Retired · 2026-03-09Multimodal modelGemini ProGemini 3.0

Gemini 3.0 Pro preview-11-2025

Release date: 2025-11-18Updated: 2026-09-13Retired: 2026-03-09Views: 3,865

Live demoGitHubHugging FaceCompare

Parameters

No data

Context length

1000K

Multilingual

Supported

Reasoning ability

5/5

Gemini 3.0 Pro (Preview 11-2025) is a multimodal model from Google Deep Mind, released on 2025-11-18. It accepts text, image, audio, and video input and returns text and audio output. The recorded context window is 1000K, and the recorded maximum output is 64K. Cataloged capabilities include Reasoning model and Multilingual. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.

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 Pro (Preview 11-2025)

Model basics

Reasoning traces

Supported

Thinking modes

Standard ModeThinking Level · DeepThinking ModeThinking Level · 4KThinking Level · 8KThinking Level · 16KThinking Level · 32KThinking Level · 64K

Context length

1000K tokens

Max output length

64K tokens

Model type

Multimodal model

Modality (in / out)

Text, Image, Audio, Video → Text, Audio

Release date

2025-11-18

Model file size

No data

MoE architecture

No

Total params / Active params

No data / Not applicable

Knowledge cutoff

No data

Gemini 3.0 Pro (Preview 11-2025)

Open source & experience

Code license

Proprietary

Weights license

Proprietary

GitHub repo

N/A

Hugging Face

N/A

Live demo

gemini.google.com/app

Gemini 3.0 Pro (Preview 11-2025)

Official resources

Paper

DataLearnerAI blog

DataLearnerAI blog

Gemini 3.0 Pro (Preview 11-2025)

API details

API speed

3/5

💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.

Learn about pricing modes

Standard

Type	Condition	Input	Output
Text	-	$2.00/ 1M tokens	$12.00/ 1M tokens
Text	Context > 200000	$4.00/ 1M tokens	$18.00/ 1M tokens

Batch

Type	Condition	Input	Output
Text	-	$1.00/ 1M tokens	$6.00/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Gemini 3.0 Pro (Preview 11-2025)

Benchmark Results

Gemini 3.0 Pro (Preview 11-2025) currently shows benchmark results led by LiveCodeBench (2 / 250, score 92), MMLU Pro (2 / 176, score 90), τ²-Bench - Telecom (8 / 264, score 98). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

General Knowledge

15 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

90

2 / 176

Thinking Mode

75

80 / 147

High

87.50

56 / 147

Low

63.90

55 / 117

High

73.39

20 / 117

unknown

37.52

148 / 563

Low

29.50

209 / 563

Thinking Mode

37.50

149 / 563

High

39.70

134 / 563

High

37.20

153 / 563

HighTools

45.80

78 / 563

High

41

124 / 563

Thinking Mode

31.10

78 / 136

High

45.10

68 / 136

High

9.10

76 / 200

General Evaluation

4 evaluations

Benchmark / mode

Score

Rank/total

Low

88.70

108 / 462

Thinking Mode

91.90

55 / 462

High

90.80

67 / 462

High

93.80

20 / 462

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

72.10

6 / 47

Coding and Software Engineer

4 evaluations

Benchmark / mode

Score

Rank/total

Low

85.70

27 / 250

Thinking Mode

92

2 / 250

High

91.70

4 / 250

SWE-bench Verified

Thinking Mode

76.20

36 / 116

Math and Reasoning

7 evaluations

Benchmark / mode

Score

Rank/total

Low

86.70

70 / 215

Thinking Mode

95

30 / 215

High

95.70

26 / 215

Thinking Mode

90.60

24 / 29

Thinking Mode

38

10 / 60

FrontierMath - Tier 4

Standard Mode

18.80

16 / 80

FrontierMath - Tier 4

Thinking Mode

18.80

16 / 80

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Thinking Mode

76.40

11 / 93

Agent Level Benchmark

7 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

LowTools

68.10

141 / 264

τ²-Bench - Telecom

Thinking ModeTools

98

8 / 264

τ²-Bench - Telecom

HighTools

87.10

74 / 264

Thinking ModeTools

85.40

8 / 44

Terminal Bench Hard

LowTools

34.10

82 / 244

Terminal Bench Hard

Thinking ModeTools

39

55 / 244

Terminal Bench Hard

HighTools

41.70

48 / 244

Instruction Following

4 evaluations

Benchmark / mode

Score

Rank/total

Low

49.70

159 / 282

Thinking Mode

70

71 / 282

High

70.40

68 / 282

HighTools

70

71 / 282

AI Agent - Information Search

1 evaluations

Benchmark / mode

Score

Rank/total

HighTools

59.20

40 / 57

AI Agent - Tool Usage

3 evaluations

Benchmark / mode

Score

Rank/total

Standard ModeTools

70.30

29 / 43

Terminal Bench 2.0

Thinking ModeTools

54.20

30 / 48

Terminal Bench 2.0

HighTools

56.90

26 / 48

Productivity Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

High

35

12 / 15

Long Context

1 evaluations

Benchmark / mode

Score

Rank/total

High

71

98 / 170

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

Thinking ModeTools

70.70

32 / 38

Multimodal Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

High

80.20

42 / 227

View benchmark analysis Compare with other models

Gemini 3.0 Pro (Preview 11-2025)

Publisher

Google Deep Mind

View publisher details

Gemini 3.0 Pro preview-11-2025

Model Overview

Gemini 3.0 Pro (Preview 11-2025) is a multimodal model from Google Deep Mind, released on 2025-11-18.

It accepts text, image, audio, and video input and produces text and audio output. Its cataloged capabilities include Reasoning model and Multilingual. The recorded context window is 1000K, and the recorded maximum output is 64K.

The model weights are proprietary and are not published for download. The page records 6 API pricing rules from Google Deep Mind; current provider pricing and conditions should be checked before deployment. The evaluation section contains 36 cataloged benchmark results with their recorded modes and scores. The page links 3 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

Gemini 3.0 Pro (Preview 11-2025)

FAQ

What is Gemini 3.0 Pro (Preview 11-2025)?

Gemini 3.0 Pro (Preview 11-2025) is a multimodal model from Google Deep Mind, released on 2025-11-18. It accepts text, image, audio, and video input and returns text and audio output. The recorded context window is 1000K, and the recorded maximum output is 64K. Cataloged capabilities include Reasoning model and Multilingual. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does Gemini 3.0 Pro (Preview 11-2025) support?

The current model record lists text, image, audio, and video as input and text and audio as output.

What are the main recorded specifications for Gemini 3.0 Pro (Preview 11-2025)?

The recorded context window is 1000K, and the recorded maximum output is 64K. Fields without a source-backed value remain undisclosed.

Does Gemini 3.0 Pro (Preview 11-2025) have API pricing?

The page records 6 API pricing rules from Google Deep Mind; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for Gemini 3.0 Pro (Preview 11-2025)?

The evaluation section contains 36 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Gemini 3.0 Pro (Preview 11-2025) open source?

The model weights are proprietary and are not published for download. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

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

DataLearner WeChat QR code